midterm

合集下载

机器学习期中考试 midterm

10-701Midterm Exam,Spring20111.Personal info:•Name:•Andrew account:•E-mail address:2.There are14numbered pages in this exam(including this cover sheet).3.You can use any material you brought:any book,notes,and print outs.You cannotuse materials brought by other students.4.No computers,PDAs,phones or Internet access.5.If you need more room to answer a question,use the back of the preceding page.6.Work eﬃciently.Consider answering all of the easier questionsﬁrst.7.There is one optional extra credit question,which will not aﬀect the grading curve.Itwill be used to bump your grade up,without aﬀecting anyone else’s grade.8.You have80minutes,the test has100points.Good luck!Question Topic Max.score Score1Short Questions202Bayes Nets233Decision Surfaces and Training Rules124Linear Regression205Conditional Independence Violation256[Extra Credit]Violated Assumptions61[20Points]Short Questions1.1True or FalseAnswer each of the following True of False.If True,give a short justiﬁcation.If False,a counter-example or convincing one-sentence explanation.1.[2pts]If we train a Naive Bayes classiﬁer using inﬁnite training data that satisﬁes allof its modeling assumptions(e.g.,conditional independence),then it will achieve zero training error over these training examples.2.[2pts]If we train a Naive Bayes classiﬁer using inﬁnite training data that satisﬁes allof its modeling assumptions(e.g.,conditional independence),then it will achieve zero true error over test examples drawn from this same distribution.3.[2pts]Every Bayes Net deﬁned over10variables X1,X2,...X10 tells how to factorthe joint probability distribution P(X1,X2,...X10)into the product of exactly10 terms.Consider the three Bayes Nets shown below:A B C4.[3pts]True or false:Every joint distribution P(X1,X2,X3)that can be deﬁned byadding Conditional Probability Distributions(CPD)to Bayes Net graph A can also be expressed by appropriate CPD’s for Bayes Net graph B.5.[3pts]True or false:Every joint distribution P(X1,X2,X3)that can be deﬁnedby adding Conditional Probability Distributions to Bayes Net graph A can also be expressed by appropriate CPD’s for Bayes Net graph C.1.2Quick questionsAnswer each of the following in one or two sentences,in the space provided.1.[2pts]Prove that P(X1|X2)P(X2)=P(X2|X1)P(X1).(Hint:This is a two-lineproof.)2.[3pts]Consider a decision tree learner applied to data where each example is describedby10boolean variables X1,X2,...X10 .What is the VC dimension of the hypothesis space used by this decision tree learner?3.[3pts]Consider the plot below showing training and test set accuracy for decisiontrees of diﬀerent sizes,using the same set of training data to train each tree.Describe in one sentence how the training data curve(solid line)will change if the number of training examples approaches inﬁnity.In a second sentence,describe what will happen to the test data curve under the same condition.2[23Points]Bayes Nets2.1[17pts]InferenceIn the following graphical model,A,B,C,and D are binary random variables.1.[2pts]How many parameters are needed to deﬁne the Conditional Probability Dis-tributions(CPD’s)for this Bayes Net?2.[2pts]Write an expression for the probability P(A=1,B=1,C=1,D=1)interms of the Bayes Net CPD e notation like P(C=1|A=0)to denote speciﬁc parameters in the CPD’s.3.[3pts]Write an expression for P(A=0|B=1,C=1,D=1)in terms of the BayesNet Conditional Probability Distribution(CPD)parameters.4.[2pts]True or False(give brief justiﬁcation):C is conditionally independent of Bgiven D.5.[2pts]True or False(give brief justiﬁcation):C is conditionally independent of Bgiven A.Suppose we use EM to train the above Bayes Net from the partially labeled data given below,ﬁrst initializing all Bayes net parameters to0.5.A B C D10101?01110?0?0?010?6.[2pts]How many distinct quantities will be updated during theﬁrst M step?7.[2pts]How many distinct quantities will be estimated during theﬁrst E step?8.[2pts]When EM converges,what will be theﬁnal estimate for P(C=0|A=1)?[Hint:You do not need a calculator.]2.2[6pts]Constructing a Bayes netDraw a Bayes net over the random variables{A,B,C,D}where the following conditional independence assumptions hold.Here,X⊥Y|Z means X is conditionally independent of Y given Z,and X ⊥Y|Z means X and Y are not conditionally independent given Z,and∅stands for the empty set.•A⊥B|∅•A ⊥D|B•A⊥D|C•A ⊥C|∅•B ⊥C|∅•A ⊥B|D•B⊥D|A,C3[12Points]Decision Surfaces and Training Rules Consider a classiﬁcation problem with two boolean variables X1,X2∈{0,1}and label Y∈{0,1}.In Figure1we show two positive(“+”)and two negative(“-”)examples.Figure1:Two positive examples and two negative examples.Question[2pts]:Draw(or just simply describe)a decision tree that can perfectly classify the four examples in Figure1.Question[3pts]:In the class we learned the training rule to grow a decision tree: we start from a single root node and iteratively split each node using the“best”attribute selected by maximizing the information gain of the split.We will stop splitting a node if: 1)examples in the node are already pure;or2)we cannotﬁnd any single attribute that gives a split with positive information gain.If we apply this training rule to the examples in Figure1,will we get a decision tree that perfectly classiﬁes the examples?Brieﬂy explain what will happen.Question[5pts]:Suppose we learn a Naive Bayes classiﬁer from the examples in Figure1,using MLE(maximum likelihood estimation)as the training rule.Write down all the parameters and their estimated values(note:both P(Y)and P(X i|Y)should be Bernoulli distributions).Also,does this learned Naive Bayes perfectly classify the four examples?Question[2pts]:Is there any logistic regression classiﬁer using X1and X2that can perfectly classify the examples in Figure1?Why?4[20Points]Linear RegressionConsider a simple linear regression model in which y is the sum of a deterministic linear function of x,plus random noise .y=wx+where x is the real-valued input;y is the real-valued output;and w is a single real-valued parameter to be learned.Here is a real-valued random variable that represents noise, and that follows a Gaussian distribution with mean0and standard deviationσ;that is, ∼N(0,σ)(a)[3pts]Note that y is a random variable because it is the sum of a deterministic function of x,plus the random variable .Write down an expression for the probability distribution governing y,in terms of N(),σ,w and x.(b)[3pts]You are given n i.i.d.training examples{(x1,y1),(x2,y2),...,(x n,y n)}to train this model.Let Y=(y1,...,y n)and X=(x1,...,x n),write an expression for the conditional data likelihood:p(Y|X,w).(c)[9pts]Here you will derive the expression for obtaining a MAP estimate of w from the training data.Assume a Gaussian prior over w with mean0and standard deviationτ(i.e.w∼N(0,τ)).Show thatﬁnding the MAP estimate w∗is equivalent to solving the following optimization problem:w∗=argmin w 12ni=1(y i−wx i)2+λ2w2;Also express the regularization parameterλin terms ofσandτ.(d)[5pts]Above we assumed a zero-mean prior for w,which resulted in the usualλ2w2regularization term for linear regression.Sometimes we may have prior knowledge that suggests w has some value other than zero.Write down the revised objective function that would be derived if we assume a Gaussian prior on w with meanµinstead of zero(i.e.,if the prior is w∼N(µ,τ)).5[25Points]Conditional Independence Violation 5.1Naive Bayes without Conditional Independence Violation Table 1:P (Y )Y =0Y =10.80.2Table 2:P (X 1|Y )X 1=0X 1=1Y =00.70.3Y =10.30.7Consider a binary classiﬁcation problem with variable X 1∈{0,1}and label Y ∈{0,1}.The true generative distribution P (X 1,Y )=P (Y )P (X 1|Y )is shown as Table 1and Table 2.Question [4pts]:Now suppose we have trained a Naive Bayes classiﬁer,using inﬁnite training data generated according to Table 1and Table 2.In Table 3,please write down the predictions from the trained Naive Bayes for diﬀerent conﬁgurations of X 1.Note that ˆY (X 1)in the table is the decision about the value of Y given X 1.For decision terms in the table,write down either ˆY=0or ˆY =1;for probability terms in the table,write down the actual values (and the calculation process if you prefer,e.g.,0.8∗0.7=0.56).Table 3:Predictions from the trained Naive BayesˆP (X 1,Y =0)ˆP (X 1,Y =1)ˆY(X 1)X 1=0X 1=1Question [3pts]:What is the expected error rate of this Naive Bayes classiﬁer on testing examples that are generated according to Table 1and Table 2?In other words,P (ˆY (X 1)=Y )when (X 1,Y )is generated according to the two tables.Hint:P (ˆY(X 1)=Y )=P (ˆY (X 1)=Y,X 1=0)+P (ˆY (X 1)=Y,X 1=1).5.2Naive Bayes with Conditional Independence Violation Consider two variables X 1,X 2∈{0,1}and label Y ∈{0,1}.Y and X 1are still generated according to Table 1and Table 2,and then X 2is created as a duplicated copy of X 1.Question[6pts]:Now suppose we have trained a Naive Bayes classiﬁer,using inﬁnite training data that are generated according to Table1,Table2and the duplication rule. In Table4,please write down the predictions from the trained Naive Bayes for diﬀerent conﬁgurations of(X1,X2).For probability terms in the table,you can write down just the calculation process(e.g.,one entry might be0.8∗0.3∗0.3=0.072,and you can just write down0.8∗0.3∗0.3to save some time).Hint:the Naive Bayes classiﬁer does assume that X2is conditionally independent of X1given Y.Table4:Predictions from the trained Naive BayesˆP(X,X2,Y=0)ˆP(X1,X2,Y=1)ˆY(X1,X2)1X1=0,X2=0X1=1,X2=1X1=0,X2=1X1=1,X2=0Question[3pts]:What is the expected error rate of this Naive Bayes classiﬁer on testing examples that are generated according to Table1,Table2and the duplication rule?Question[3pts]:Compared to the scenario without X2,how does the expected error rate change(i.e.,increase or decrease)?In Table4,the decision ruleˆY on which conﬁgura-tion is responsible to this change?What actually happened to this decision rule?(You need to brieﬂy answer:increase or decrease,the responsible conﬁguration,and what happened.)5.3Logistic Regression with Conditional Independence Violation Question[2pts]:Will logistic regression suﬀer from having an additional variable X2that is actually a duplicate of X1?Intuitively,why(hint:model assumptions)?Now we will go beyond the intuition.We have a training set D1of L examples D1={(X11,Y1),...,(X L1,Y L)}.Suppose we generate another training set D2of L examples D2={(X11,X12,Y1),...,(X L1,X L2,Y L)},where in each example X1and Y are the same as in D1and then X2is a duplicate of X1.Now we learn a logistic regression from D1,which should contain two parameters:w0and w1;we also learn another logistic regression from D2,whichshould have three parameters:w0,w1and w2.Question[4pts]:First,write down the training rule(maximum conditional likelihoodestimation)we use to estimate(w0,w1)and(w0,w1,w2)from data.Then,given the trainingrule,what is the relationship between(w0,w1)and(w0,w1,w2)we estimated from D1andD2?Use this fact to argue whether or not the logistic regression will suﬀer from having an additional duplicate variable X2.6[Extra Credit 6pts]Violated assumptionsExtra Credit Question :This question is optional –do not attempt it until you have completed the rest of the exam.It will not aﬀect the grade curve for the exam,though you will receive extra points if you answer it.Let A,B,and C be boolean random variables governed by the joint distribution P (A,B,C ).Let D be a dataset consisting of n data points,each of which is an independent draw from P (A,B,C ),where all three variables are fully observed.Consider the following Bayes Net,which does not necessarily capture the correct condi-tional independencies in P (A,B,C).Let ˆPbe the distribution learned after this Bayes net is trained using D .Show that for any number ,0< ≤1,there exists a joint distribution P (A,B,C )such that P (C =1|A =1)=1,but such that the Bayes net shown above,when trained on D ,will (with probability1)learn CPTs where:ˆP (C =1|A =1)= b ∈{0,1}ˆP(C =1|B =b )ˆP (B =b |A =1)≤ as |D |approaches ∞.Assume that the Bayes net is learning on the basis of the MLE.You should solve this problem by deﬁning a distribution with the above property.Your ﬁnal solution may be either in the form of a fully speciﬁed joint distribution (i.e.you write out the probabilities for each assignment of the variables A,B,and C ),or in the form of a Bayes net with fully speciﬁed CPTs.(Hint:the second option is easier.)。

midterm 2015 Student version 1 trial

Faculty of Economics and Business Academic year 2014-2015 On the first page of this exam form you will find important information about thisexam.Please read the information below before answering any exam questions!Exam: Financiering (6011P0122) and Finance (6011P0135)Date and time of the exam: Tuesday, April 21Duration of the exam: 1 ½ hourYou have to identify yourself using your validated UvA-identification card or other legal ID-card.If you are not registered via SIS for the course component correctly, your exam will not be marked andregistered.Please write your name and student number on everysheet of paper you hand in.Warning against cheating: Do not cheat! Students who are caught in any form of cheating will be punished, the maximum punishment being exclusion from all exams for a period of one year.Make sure that your mobile phone is switched off and locked in your briefcase. Your briefcase must be closedand placed on the floor.During the exam you are not allowed to go to the toilet without the prior consent ofthe coordinating supervisor or invigilator.Tools allowed:<pencil, pen, eraser, ruler, (non-graphic) calculator, dictionary.> Specific information on this exam: <15 multiple choice questions equally weighted.>Version code 1Please fill in the version code on your answer sheet before you start.On the answer sheet, Answer A corresponds with 1, B with 2, C with 3 and D with 4 The results of this exam will be published within 15 working days following the date of the exam. If the re-sit is scheduled to take place within 6 weeks following the current exam, the results of the current exam will be published within 12 working days.Inspection of the exam: <on request by e-mail>You may ask for copies of the assessed work and the elaborations/solutions, at cost price.You are allowed to keep the question form(s) after the examination.Good luck!Question 1Which of the following statements is most correct?A) An advantage to incorporation is that it allows for less regulation of the business.B) An advantage of a corporation is that it is subject to double taxation.C) Unlike a partnership, a disadvantage of a corporation is that it has unlimited liability.D) Corporations face more regulations when compared to partnerships.Answer: DQuestion 2Consider three securities that pay risk-free cash flows over the next three years.Security: Cash Flow in one year Cash Flow in two years Cash flow in three years B1 $100 $0 $0B2 $0 $0 $100B3 $0 $100 $0If the current risk-free interest rate were 10%, what is the no-arbitrage price of a security that pays cash flows of $100 in one year, $100 in two years and $300 in three years?A)$331.32B)$398.94C)$248.68D)$413.96Answer B: First calculate the present values of all securities:PPPP BB1$1001.1=$90.91 ; PPPP BB2$1001.13=$75.13 ; PPPP BB3$1001.12=$82.64Now match the cash flows per year to mimic the security:No−arbitrage price=$90.91+$82.64+3∗$75.13=$398.94Question 3In early 2010, Apple Inc. had a book value of equity of $205 billion, 10.5 billion shares outstanding, and a market price of $35.80 per share. Apple also had cash of $70 billion and total debt of $112 billion.Apple’s Enterprise Value in early 2010 was closest to?A)$375.9 billionB)$333.9 billionC)$374.93 billionD)$417.9 billion.Answer d: EV=Market capitalization+Total Debt−CashEV=10.5∗$35.8+$112−$70=$417.9 billionQuestion 4Which of the following adjustments to net income is not correct if you are trying to calculate cash flow from operating activities?A) Add increases in accounts payableB) Add back depreciationC) Add increases in accounts receivableD) Deduct increases in inventoryAnswer: CQuestion 5Analysts often classify firms with high market-to-book ratios as:A)Value StocksB)Promising StocksC)Investment Grade StocksD)None of the above.D) These are growth stocks Answer d: page 28Question 6Consider the two following two statements:I: If the discount rate is negative, you’d rather have a certain dollar tomorrow than today.II: You can ignore compounding or discounting when evaluating the present value of a project that only takes 1 year.Of these statementsA)I is true, II is false;B)I is false, II is trueC)Both are trueD)Both are falseAnswer: Correct answer: AQuestion 7Suppose, you want to be a millionaire in 10 years. How much will you have to put aside each year at the end of the year in order to become one? Assume that the interest rate is 7% and your first deposit is at the end of this year. The minimal amount you will have to put aside each year is closest to:A) €72,378.B) €75,868.C) €100,000.D) €142,378.Correct answer: AAnswer: Ann=FV*r/((1+r)^n-1) =1,000,000*0.07/(1.07^10-1)=72,378Question 8Consider a security that pays €750 per year for the next 20 years. The first payment is today and the discount rate is equal to 4.5%. The value of this security today is closest to:A) €9,445.B) €9,756.C) €10,195.D) €10,506.Correct answer: CCorrect answer: CAnswer: PV=Ann*(1-(1+r)^(-n))/r*(1+r)=750*(1-1.045^(-20))/0.045*1.045=10,195 Question 9Suppose you want the highest interest possible on you savings account at which you deposit €1,000 today. You withdraw this amount after one year. Which savings account would you choose out of the following? The given interest rates are Annual Percentage Rates (APR).A) 10.4% per year compounded annually.B) 10.3% per year compounded semi-annually.C) 10.1% per year compounded quarterly.D) 10% per year compounded daily.Correct answer: BAnswer: gross interest p.a. = (1+r/m)^m - 1 , with m periods in a yearFor A: 10,4%For B: 10,565%For C: 10.489%For D: 10.516% (m=365)Question 10You have an investment opportunity in Germany that requires an investment of $250,000 today and will produce a cash flow of €208,650 in one year with no risk. Suppose the risk-free rate of interest in Germany is 6% and the current competitive exchange rate is €0.78 to $1.00. What is the NPV of this project in dollars? Would you take the project?A) NPV = 0; NoB) NPV = -$2,358; NoC) NPV = $2,358; YesD) NPV = $13,650; YesAnswer: CExplanation: C) NPV = -250,000 + (€208,650 / 1.06) × $1.00 / €0.78 = $2358, so since NPV > 0, acceptQuestion 11You are considering investing in a start-up project at a cost of $100,000 now. You expect the project to return a one-time cash flow of $500,000 to you seven years from now. Given the risk of this project, your opportunity cost of capital is 20%.The decision you should take regarding this project is:A) reject the project since the NPV is negative.B) reject the project since the NPV is positive.C) accept the project since the IRR < 20%.D) accept the project since the IRR > 20%.Answer: DExplanation: D) IRR= - 1 = .25849895NPV = -100,000 + 500,000/(1.20)7 = 39,540.82Therefore we should accept because NPV > 0 and because IRR > 20%.Question 12Which of the following statements is FALSE?A) In general, the difference between the cost of capital and the IRR is the maximum amount of estimation error in the cost of capital estimate that can exist without altering the original decision.B) If the cost of capital estimate is more than the IRR, and the project is characterized with first (a) negative cash flow(s) followed by positive cash flows, the NPV will be positive.C) If you are unsure of your cost of capital estimate, it is important to determine how sensitive your analysis is to errors in this estimate.D) The IRR can provide information on how sensitive your analysis is to errors in the estimate of your cost of capital.Answer: BExplanation: B) If the cost of capital estimate is more than the IRR, and the NPV is a negative function of the discount rate, the NPV will be negative.Question 13Consider a project with the following cash flows:Year Cash Flow0 -10,0001 4,0002 4,0003 4,0004 4,000Assume the appropriate discount rate for this project is 15%. The profitability index for this project is closest to:A) .14B) .22C) .60D) .15Answer: AExplanation: A) NPV = -10,000 + + + + = $1420PI = NPV/investment = 1420/10000 = .1420Question 14Which of the following statements is FALSE?A) Because value is lost when a resource is used by another project, we should include the opportunity cost of that resource as an incremental cost of the project.B) Sunk costs are incremental with respect to the current decision regarding the project and should be included in its analysis.C) Overhead expenses are associated with activities that are not directly attributable to a single business activity but instead affect many different areas of the corporation.D) When computing the incremental earnings of an investment decision, we should include all changes between the firm's earnings with the project versus without the project. Answer: BQuestion 15Taggart Transcontinental is considering adding a trucking division to expand the coverage of its existing rail lines. The trucking division will cost $1,000,000 upfront and is expected to generate free cash flows of $100,000 at the end of each of the next five years. Taggart Transcontinental forecasts that future free cash flows after year 5 will grow at 2% per year, forever. Taggart Transcontinental's cost of capital is 10%.The NPV for the trucking division is closest to:A) 170,750B) 200,000C) 212,550D) 250,000Answer: ANPV = -1,000,000 + 100,000/0.1(1 – 1/1,1^5) + 1/1.1^5 100,000(1.02)/(.10 - .02)Formula sheet Financiering / Finance。

考试的英语周记(汇总5篇)

考试的英语周记（汇总5篇）1.考试的英语周记第1篇Midterm exams are as important as final exams, and sometimes they are extraordinary. A good test, felt, followed by the teacher's praise, the envy of the students and parents the joy; do not, the teacher will be disappointed, parents will be angry, may also face contempt and ridicule classmates have the vision of discourse. In my humble opinion, the exam is good, and the exam is not good, do not lose heart, if you want to consider the praise of elders, under the consideration of the cynicism of the students, will be defeated undoubtedly. Examination is not arrogant, the exam is not discouraged, to be mediocre and mentalattitude should be tested, but can do well. But when it comes to easy,it's hard to do it.Let's take this midterm exam. I was holding on double percent confidence to test. From morning to night, after examination, very tired and worried, time seems to stand still, slowly, do well and do well the two words in the heart to fight, sleep at night sleep to feel better.The second day is the math test. When I finished the exam, I went around asking the answer to the math, so as to answer my own answer, followed by a few words!" Cheers, because I felt like I was 100. Now look at the language. I was as nervous as a few rabbits in my heart, and I could clearly feel the rhythm of my heart beat. At this time, my classmate Xiong Mengfei ran his cool hands on my shoulder, said: "don't be upset," heard that, my heart thump look, he continued: "you Chinese long to pick up at five five." Ah! How did that happen?! Suddenly, my eyes emerge out of this a few picture: Grandpa and I sat in the living room, Grandpa asked me if I was 100, I said 99 - 9999% grasp 100 points; my mother and I pulled the: Double percent reward one hour of computer game. Now, not only to live up to the expectations of a grandfather, and hours of game has become a bubble! Oh! Why is that so?! I pray in my heart: I wish math could give me a satisfactory result!I hope your exam in a calm state of mind, but do Zhennan ah!2.考试的英语周记第2篇Finally, it's time for the mid-term exam.Day by day to time, the number is getting smaller and smaller, let me smell the smoke of the mid-term exam, the heart is full of tension. A little scared, a little flustered, a little happier. Sometimes I feel uneasy, somehow, in order to approach the mid-term exam, or to endless test.These days, I remember something and I forgot it. I cried in my heart: "I can't stand it."." Teacher to me, you have no way out, in addition to difficulties, retreat is coward. So I want to be a brave person, brave to face difficulties, overcome difficulties. Mid term exams often make us feel pain and happiness, but only those who can overcome the pain can win the happiness that belongs to us!I believe you have seen dancing butterflies, praised its beauty. But who has noticed the moment when the pupa becomes butterfly? When I have witnessed the process of cocoon and pupa in the shell desperately struggling, the process is so painful, shedding pupa shell moment, seems to be able to hear the sound of heart, but the pupa persist with confidence and faith is the longing for the future, it insisted, don't give up, bear pain, good attitude adjustment, to overcome the pain! It finally succeeded! Trembling wings gradually unfolded, beautiful figure flying in the air......In fact, our mid-term exam is trueas, to escape the pain, I will always be an ugly pupa; to fight bravely face the reality, adjust good mentality, to shed bitter shell, we will become a beautiful butterfly! Hold on, boys!Day by day, our beautiful butterfly is gradually forming.I know that, after a few days, I will break the butterfly cocoon thick bound, with all the pride of the beautiful off, and other partners together to create a miracle, together to create a very grand Diewu event.3.考试的英语周记第3篇Thursday morning, I came to the classroom, or as usual, the class is noisy.After a bell sound, but also the noisy classroom suddenly in perfect silence. A tense atmosphere hung over the whole classroom. The teacher send us mid-term exam papers, and then gave the order. The classroom can only hear the sound of the writing brush. My heart seems to put a little rabbit like, "they came, not the" beating. Because of the tense mood temporarily difficult to calm, I secretly looked around the classmates. In the face of the same exam questions, everyone's expression is verydifferent. Some people kept writing, like writing if there is spirit; some people stretched his neck up, stared at the paper of others; some people frowned, bean big sweat came out...... As time passed, I answered the questions immediately.I was tired of writing, and I wanted to see what Li Luoxin did next. Who knew I had just twisted my head, and he covered the paper with his hand, as if I wanted to copy his answer. I thought to myself, "how wonderfuldo you think your grades are?"! I'm going to copy you. Hum! I turned my head again and made my own paper. At this time, someone asked softly: "Hey, I don Cenyu third questions, fifth questions how to do ah!" I looked at the question he asked, and then continued answering the paper as if I hadn't heard it. After 10 minutes, the man asked me to have the problem how to do, I put your cards on the table and said to him: "Idon't know!"After a short time, the invigilator said, "only 15 minutes left from the winding up, and a roll of the bell after the class is called."." The students listen to this, I also like a badly frightened person, to write is not finished the composition. I didn't know if it was a coincidence.I just finished my composition and the bell rang after class. Theteacher said, "roll up."!" At this time, the classroom was bustling again.Hey! I am a sigh. The tense mid-term exam is finally over!4.考试的英语周记第4篇Today, on the day of the midterm. I came to school early and reviewed it seriously. After half an hour, Professor Fu walked into the classroom with a stack of examination papers, and the tense examination began.I was absorbed in answering the test paper. Unconsciously, I have read the questions, which is my biggest headache. I frowned, read the article, and began to answer questions. I in front of a few I can barely cope, behind more and more difficult. To the fourth question, I didn't have a clue, do not go completely."What shall I do?" Time is precious, hey! Go!"After such an ideological struggle. I was half guessing, and the pen in my hand was moving on the paper.Suddenly, the last question I do, a look at the subject more silly eye, too! At this time, the voice of Fu teacher prompted: "there are still twenty-eight minutes, please seize the time."!"It's over! Time is pressing. Hurry up!" I was so excited.But then I thought: "no! Calm down to think out!" So, I read the article again. Sure enough, click into place, I was extremely happy, grabbed a pen and quickly answer.Remove the "stumbling block", and finally the composition. I have a good idea, he took the pen and wrote "Shua Shuashua". About half the time, there is a saying "stuck", to think, in the scratch head scratching ears, eyes bright, "the!" Continued writing.Call! Finally finished. When writing, "jingle bell!" The coiling bell rings. "What a coincidence!" I gave the examination paper to the teacher, and it was a relief.Back to my seat, I pulled out an extracurricular book to relieve myself......"Jingle bell!" The bell rings again in the second exam. "So fast."!" I packed up my extracurricular books and began to receive the English test.I don't know how long it's been......"Hey! It's a headache choice!"5.考试的英语周记第5篇On Thursday, our school held the mid-term exam midterm exam, finally finished, a stone fell in my heart, but there is a big stone pressed me out of breath, that is the score of the examination. After class, the students were talking about problems and scores, which made me nervous.In the morning of the second section of the math class, I took out the book early, listen to a few classmates said I scored 93 points. But I'm still worried, what if they're wrong? In this way, in a tense atmosphere, the mathematics teacher walked into the classroom, holding our volume in the arms. "I'll give you a grade!" The math teacher said, picked up the test paper. At this moment, the air in the classroom suddenly solidified, and the students' faces were full of anxiety and worry. The grades ofthe students are good and bad. Heard some achievements, immediately become jubilant, others become dejected and despondent, beam with joy; regret, regret did not seriously review. The classroom was plunged intoa tense atmosphere. At this time, my heart in his throat, palms began to sweat. "Qiu Renyuan, 93!" Not bad. The big stone in my heart fell down. When the test paper was sent out, I hurried to find mistakes in the examination paper. When I was in the equation, I wrote down the numbers above. I said to myself, "how can you be so careless?"!". Chinese, science papers also sent down, Chinese exam *5 points, the science exam 96 points.I think my biggest fault is carelessness. I have declared war on carelessness countless times, but each time it ended in failure. Often make jokes, I became the laughingstock of the classmates. Another drawback is that you don't take the exam seriously. When I was doing the test, I felt the time was so tight that I could do it very quickly. Sometimes I can't even see my own words.I must be careful in the future examination, do the title to see clearly, then write. Later, I want to make persistent efforts, develop good habits, and strive for better results!。

MIDTERM 1

Name: ________________________ Class: ___________________ Date: __________ ID: A MidtermMultiple ChoiceIdentify the choice that best completes the statement or answers the question.____ 1. In economics, the cost of something isa.the dollar amount of obtaining it.b.always measured in units of time given up to get it.c.what you give up to get it.d.often impossible to quantify, even in principle.____ 2. Mallory decides to spend three hours working overtime rather than watching a video with her friends. She earns $8 an hour. Her opportunity cost of working isa.the $24 she earns working.b.the $24 minus the enjoyment she would have received from watching the video.c.the enjoyment she would have received had she watched the video.d.nothing, since she would have received less than $24 of enjoyment from the video.____ 3. Teresa eats three oranges during a particular day. The marginal benefit she enjoys from eating the third orangea.can be thought of as the total benefit Teresa enjoys by eating three oranges minus thetotal benefit she would have enjoyed by eating just the first two oranges.b.determines Teresa’s willingness to pay for the first, second, and third oranges.c.does not depend on how many oranges Teresa has already eaten.d.All of the above are correct.____ 4. If the price of visiting a doctor were fixed below the current price, then we would expecta.an increase in the number of visits people want to make and an increase in the number ofvisits health care providers want to provide.b.an increase in the number of visits people want to make and a decrease in the number ofvisits health care providers want to provide.c. a decrease in the number of visits people want to make and an increase in the number ofvisits health care providers want to provide.d. a decrease in the number of visits people want to make and a decrease in the number ofvisits health care providers want to provide.____ 5. Which of the following transactions does not take place in the markets for factors of production in the circular-flow diagram?a. a landowner leases land to a farmerb. a farmer hires a teenager to help with harvestc. a retired farmer sells his combine to a new farmerd. a woman buys corn for dinner____ 6. Refer to Figure 2-1. Enid completes her first week of employment working as a hairdresser at a salon. On Friday of that week, she receives her first paycheck. To which of the arrows does this transaction directlycontribute?a. B onlyb. A and Bc. C onlyd. C and D____ 7. Suppose a nation is currently producing at a point inside its production possibilities frontier. We know thata.the nation is producing beyond its capacity, so inflation will occur.b.the nation is not using all available resources or is using inferior technology or both.c.the nation is producing an efficient combination of goods.d.there will be a large opportunity cost if the nation tries to increase production of anygood.____ 8. The bowed shape of the production possibilities frontier can be explained by the fact thata.all resources are scarce.b.economic growth is always occurring.c.the opportunity cost of one good in terms of the other depends on how much of eachgood the economy is producing.d.the only way to get more of one good is to get less of the other.____ 9. The country of Econoland produces two goods, textbooks and widgets. Last year, it produced 200 textbooks and 500 widgets. This year, it produced 250 textbooks and 600 widgets. Given no other information, whichof the following events could not explain this change?a.Econoland experienced a reduction in unemployment.b.Econoland experienced an improvement in widget-making technology.c.Econoland acquired more resources.d.Any of these events could, in fact, explain the change.____ 10. Refer to Figure 2-5. If this economy devotes one-half of its available resources to the production of baseballs and the other half to the production of bananas, it could producea.150 bananas and 100 baseballs.b.150 bananas and 150 baseballs.c.300 bananas and 200 baseballs.d.We would have to know the details of this economy’s technology in order to determinethis.Table 4-2Price Audrey’sQuantityDemandedBob’sQuantityDemandedChuck’sQuantityDemandedDottie’sQuantityDemanded$122134$104445$86756$68847$410938$2121029____ 11. Refer to Table 4-2. If these are the only four buyers in the market, then when the price decreases from $6 to $4, the market quantity demandeda.increases by 0.75 units.b.increases by 3 units.c.increases by 8 units.d.decreases by 27 units.____ 12. When quantity demanded increases at every possible price, we know that the demand curve hasa.shifted to the left.b.shifted to the right.c.not shifted; rather, we have moved along the demand curve to a new point on the samecurve.d.not shifted; rather, the demand curve has become steeper.____ 13. Which of the following would not shift the demand curve for mp3 players?a. a decrease in the price of mp3 playersb. a fad that makes mp3 players more popular among 12-25 year oldsc.an increase in the price of CDs, a complement for mp3 playersd. a decrease in the price of satellite radio, a substitute for mp3 players____ 14. Which of the following is not a determinant of demand?a.the price of a resource that is used to produce the goodb.the price of a complementary goodc.the price of the good next monthd.all of the above are determinants of demand.____ 15. If buyers today become more willing and able than before to purchase larger quantities of Vanilla Coke at each price of Vanilla Coke, thena.we will observe a movement downward and to the right along the demand curve forVanilla Coke.b.we will observe a movement upward and to the left along the demand curve for VanillaCoke.c.the demand curve for Vanilla Coke will shift to the right.d.the demand curve for Vanilla Coke will shift to the left.____ 16. The supply curve for coffeea.shifts when the price of coffee changes because the price of coffee is measured on thevertical axis of the graph.b.shifts when the price of coffee changes because the quantity supplied of coffee ismeasured on the horizontal axis of the graph.c.does not shift when the price of coffee changes because the price of coffee is measuredon the vertical axis of the graph.d.does not shift when the price of coffee changes because the quantity supplied of coffee ismeasured on the horizontal axis of the graph.____ 17. Workers at a bicycle assembly plant currently earn the mandatory minimum wage. If the federal government increases the minimum wage by $1.00 per hour, then it is likely that thea.demand for bicycle assembly workers will increase.b.supply of bicycles will shift to the right.c.supply of bicycles will shift to the left.d.firm must increase output to maintain profit levels.Table 4-7The demand schedule below pertains to sandwiches demanded per week.Price Charlie’sQuantityDemanded Maxine’sQuantityDemandedQuinn’sQuantityDemanded$3343$512x____ 18. Refer to Table 4-7. Suppose Charlie, Maxine, and Quinn are the only demanders of sandwiches. Also suppose the following:• x = 2• the current price of a sandwich is $5.00• the market quantity supplied of sandwiches is 10• the law of supply applies to the supply of sandwichesThena.there is a shortage of 5 sandwiches and the price would be expected to rise from itscurrent level of $5.00.b.there is a shortage of 5 sandwiches and the price would be expected to fall from itscurrent level of $5.00.c.there is a surplus of 5 sandwiches and the price would be expected to rise from itscurrent level of $5.00.d.there is a surplus of 5 sandwiches and the price would be expected to fall from its currentlevel of $5.00.____ 19. Music compact discs are normal goods. What will happen to the equilibrium price and quantity of music compact discs if musicians accept lower royalties, compact disc players become cheaper, more firms startproducing music compact discs, and music lovers experience an increase in income?a.Price will fall and the effect on quantity is ambiguous.b.Price will rise and the effect on quantity is ambiguous.c.Quantity will fall and the effect on price is ambiguous.d.Quantity will rise and the effect on price is ambiguous.____ 20. What would happen to the equilibrium price and quantity of peanut butter if the price of peanuts went up, the price of jelly fell, fewer firms decided to produce peanut butter, and health officials announced that eatingpeanut butter was good for you?a.Price will fall and the effect on quantity is ambiguous.b.Price will rise and the effect on quantity is ambiguous.c.Quantity will fall and the effect on price is ambiguous.d.Quantity will rise and the effect on price is ambiguous.____ 21. Which of the following is correct?a.The market value of rental housing services is included in GDP, but the market value ofowner-occupied housing services is not.b.The market value of owner-occupied housing services is included in GDP, but the marketvalue of rental housing services is not.c.The market values of both owner-occupied housing services and rental housing servicesare included in GDP.d.Neither the market value of owner-occupied housing services nor the market value ofrental housing services is included in GDP.____ 22. Ralph pays someone to mow his lawn, while Mike mows his own lawn. Regarding these two practices, which of the following statements is correct?a.Only Ralph’s payments are included in GDP.b.Ralph’s payments as well as the estimated value of Mike’s mowing services are includedin GDP.c.Neither Ralph’s payments nor the estimated value of Mike's mowing services is includedin GDP.d.Ralph’s payments are definitely included in GDP, while the estimated value of Mike’smowing services is included in GDP only if Mike voluntarily provides his estimate ofthat value to the government.____ 23. One bag of flour is sold for $1.00 to a bakery, which uses the flour to bake bread that is sold for $3.00 to consumers. A second bag of flour is sold to a consumer in a grocery store for $2.00. Taking these threetransactions into account, what is the effect on GDP?a.GDP increases by $2.00.b.GDP increases by $3.00.c.GDP increases by $5.00.d.GDP increases by $6.00.____ 24. In 2007, Corny Company grows and sells $2 million worth of corn to Tasty Cereal Company, which makes corn flakes. Tasty Cereal Company produces $6 million worth of corn flakes in 2007, with sales tohouseholds during the year of $4.5 million. The unsold $1.5 million worth of corn flakes remains in TastyCereal Company’s inventory at the end of 2007. The transactions just described contribute how much to GDPfor 2007?a.$4.5 millionb.$6 millionc.$6.5 milliond.$8 million____ 25. Anna, a U.S. citizen, works only in Germany. The value she adds to production in Germany is includeda.in both German GDP and U.S. GDP.b.in German GDP, but it is not included in U.S. GDP.c.in U.S. GDP, but it is not included in German GDP.d.in neither German GDP nor U.S. GDP.____ 26. If you buy a burger and fries at your favorite fast food restaurant,a.then neither GDP nor consumption will be affected because you would have eaten athome had you not bought the meal at the restaurant.b.then GDP will be higher, but consumption spending will be unchanged.c.then GDP will be unchanged, but consumption spending will be higher.d.then both GDP and consumption spending will be higher.____ 27. A good is produced by a firm in 2007, added to the firm’s inventory in 2007, and sold to a household in 2008.It follows thata.the value of the good is added to the investment category of 2007 GDP, added to theconsumption category of 2008 GDP, and subtracted from the investment category of2008 GDP.b.the value of the good is added to the investment category of 2007 GDP, added to theconsumption category of 2008 GDP, and not included in the investment category of 2008GDP.c.the value of the good is added to the investment category of 2007 GDP, subtracted fromthe consumption category of 2008 GDP, and not included in the investment category of2008 GDP.d.the value of the good is added to the investment category of 2007 GDP, subtracted fromthe consumption category of 2008 GDP, and added to the investment category of 2008GDP.____ 28. When an Egyptian firm purchases a cement mixer from Slovakia,a.Egyptian investment does not change, Egyptian net exports decrease, Egyptian GDPdecreases, Slovakian net exports increase, and Slovakian GDP increases.b.Egyptian investment increases, Egyptian net exports decrease, Egyptian GDP isunaffected, Slovakian net exports increase, and Slovakian GDP increases.c.Egyptian investment decreases, Egyptian net exports increase, Egyptian GDP isunaffected, Slovakian net exports decrease, and Slovakian GDP decreases.d.Egyptian investment increases, Egyptian net exports do not change, Egyptian GDPincreases, Slovakian net exports do not change, and Slovakian GDP is unaffected.____ 29. An Iowan receives a Social Security check for $500, which he uses to purchase a $480 television made in Japan by a Japanese firm and a $20 dinner at a local restaurant. As a result, U.S. GDPa.does not change.b.increases by $20.c.increases by $520.d.increases by $1000.____ 30. An American soldier stationed in California receives a paycheck from the federal government for $500, which she uses to purchase a $300 stereo made in Korea by a Korean firm and $200 worth of groceries produced inCalifornia. As a result, U.S. GDP increases bya.$200.b.$500.c.$700.d.$1000.Table 23-3The table below contains data for the country of Wrexington for the year 2008.Total income$5731Household purchases of durable goods$1108Household purchases of nondurable goods$702Household purchases of non-education services$203Household purchases of education services$302Household purchases of new housing$816Purchases of capital equipment$333Inventory changes$75Purchases of new structures$267Depreciation$401Local government spending on goods and services$236State government spending on goods and services$419Federal government spending on goods and services$1182Transfer payments$707Foreign purchases of domestically produced goods$217Domestic purchases of foreign goods$129____ 31. Refer to Table 23-3. What were Wrexington’s government purchases in 2008?a.$1130b.$1601c.$1837d.$2544____ 32. Which of the following is correct?a.Nominal GDP never equals real GDP.b.Nominal GDP always equals real GDP.c.Nominal GDP equals real GDP in the base year.d.Nominal GDP equals real GDP in all years but the base year.____ 33. The GDP deflator is the ratio ofa.real GDP to nominal GDP multiplied by 100.b.real GDP to the inflation rate multiplied by 100.c.nominal GDP to real GDP multiplied by 100.d.nominal GDP to the inflation rate multiplied by 100.____ 34. If real GDP doubles and the GDP deflator doubles, then nominal GDPa.remains constant.b.doubles.c.triples.d.quadruples.____ 35. A country reported a nominal GDP of $115 billion in 2008 and $125 billion in 2007. It also reported a GDP deflator of 85 in 2008 and 100 in 2007. Between 2007 and 2008,a.real output and the price level both rose.b.real output rose and the price level fell.c.real output fell and the price level rose.d.real output and the price level both fell.Table 23-4The table below contains data for the country of Dachsland, which produces only pretzels and books. Thebase year is 2005.Year PriceofPretzels QuantityofPretzelsPriceofBooksQuantity ofBooks2005$4.0090$1.501502006$4.00100$2.001802007$5.00120$2.502002008$6.00150$3.50200____ 36. Refer to Table 23-4. Dachsland’s inflation rate from 2006 to 2007 wasa.16.4%.b.24.3%.c.41.0%.d.44.7%.____ 37. If 2004 is the base year, then the inflation rate for 2005 equalsa.CPI in2005−CPI in2004CPI in2004×100.b.CPI in2005−CPI in2004CPI in2005×100.c.CPI in2004−CPI in2005CPI in2004×100.d.CPI in2004−CPI in2005CPI in2005×100.____ 38. The price index was 150 in the first year, 160 in the second year, and 175 in the third year. The inflation rate was abouta. 6.25 percent between the first and second years, and 8.6 percent between the second andthird years.b. 6.7 percent between the first and second years, and 9.4 percent between the second andthird years.c.10 percent between the first and second years, and 15 percent between the second andthird years.d.60 percent between the first and second years, and 75 percent between the second andthird years.____ 39. If the CPI was 110 this year and 100 last year, thena.the cost of the CPI basket of goods and services increased by 110 percent this year.b.the price level increased by 10 percent this year.c.the inflation rate for this year was 10 percent higher than the inflation rate for last year.d.All of the above are correct.____ 40. When new goods are introduced, consumers have more variety from which to choose. As a result, each dollar is wortha.more, and the cost of living increases.b.more, and the cost of living decreases.c.less, and the cost of living increases.d.less, and the cost of living decreases.____ 41. Which of the following statements about the term of a bond is correct?a.Term refers to the various characteristics of a bond, including its interest rate and taxtreatment.b.The term of a bond is determined entirely by its credit risk.c.The term of a bond is determined entirely by how much sales charge the buyer of thebond pays when he or she purchases the bond.d.Interest rates on long-term bonds are usually higher than interest rates on short-termbonds.____ 42. Long-term bonds area.riskier than short-term bonds, and so interest rates on long-term bonds are usually lowerthan interest rates on short-term bonds.b.riskier than short-term bonds, and so interest rates on long-term bonds are usually higherthan interest rates on short-term bonds.c.less risky than short-term bonds, and so interest rates on long-term bonds are usuallylower than interest rates on short-term bonds.d.less risky than short-term bonds, and so interest rates on long-term bonds are usuallyhigher than interest rates on short-term bonds.____ 43. Which of the following is correct?a.Lenders sell bonds and borrowers buy them.b.Long-term bonds usually pay a lower interest rate than do short-term bonds becauselong-term bonds are riskier.c.The term junk bonds refers to bonds that have been resold many times.d.None of the above is correct.____ 44. Municipal bonds pay a relativelya.low rate of interest because of their high default risk and because the interest they pay issubject to federal income tax.b.low rate of interest because of their low default risk and because the interest they pay isnot subject to federal income tax.c.high rate of interest because of their high default risk and because federal taxes must bepaid on the interest they pay.d.high rate of interest because of their low default risk and because the interest they pay isnot subject to federal income tax.Name: ________________________ ID: A____ 45. Suppose that in a closed economy GDP is equal to 11,000, taxes are equal to 1,500, consumption equals 7,500, and government purchases equal 2,000. What is national saving?a.-500b.0c.1,500d.None of the above is correct.____ 46. For a closed economy, GDP is $11 trillion, consumption is $7 trillion, taxes are $3 trillion and the government runs a surplus of $1 trillion. What are private saving and national saving?a.$4 trillion and $1 trillion, respectivelyb.$4 trillion and $5 trillion, respectivelyc.$1 trillion and $2 trillion, respectivelyd.$1 trillion and $1 trillion, respectively____ 47. For an imaginary closed economy, T = $5,000; S = $11,000; C = $50,000; and the government is running a budget deficit of $1,000. Thena.private saving = $10,000 and GDP = $54,000.b.private saving = $10,000 and GDP = $58,000.c.private saving = $12,000 and GDP = $67,000.d.private saving = $12,000 and GDP = $72,000.____ 48. The slope of the supply of loanable funds curve represents thea.positive relation between the real interest rate and investment.b.positive relation between the real interest rate and saving.c.negative relation between the real interest rate and investment.d.negative relation between the real interest rate and saving.____ 49. Which of the following could explain a decrease in the equilibrium interest rate and in the equilibrium quantity of loanable funds?a.The demand for loanable funds shifted rightward.b.The demand for loanable funds shifted leftward.c.The supply of loanable funds shifted rightward.d.The supply of loanable funds shifted leftward.____ 50. Suppose the government were to replace the income tax with a consumption tax so that interest on savings was not taxed. The result would be that the interest ratea.and investment both would increase.b.and investment both would decrease.c.would increase and investment would decrease.d.would decrease and investment would increase.MidtermAnswer SectionMULTIPLE CHOICE1. ANS: C PTS: 1 DIF: 1 REF: 1-1NAT: Analytic LOC: Scarcity, tradeoffs, and opportunity costTOP: Opportunity cost MSC: Definitional2. ANS: C PTS: 1 DIF: 3 REF: 1-1NAT: Analytic LOC: Scarcity, tradeoffs, and opportunity costTOP: Opportunity cost MSC: Applicative3. ANS: A PTS: 1 DIF: 3 REF: 1-1NAT: Analytic LOC: Marginal costs & benefits TOP: Marginal changesMSC: Applicative4. ANS: B PTS: 1 DIF: 2 REF: 1-2NAT: Analytic LOC: Markets, market failure, and externalitiesTOP: Markets MSC: Applicative5. ANS: D PTS: 1 DIF: 2 REF: 2-1NAT: Analytic LOC: Understanding and applying economic modelsTOP: Circular-flow diagram | Factor markets MSC: Applicative6. ANS: D PTS: 1 DIF: 2 REF: 2-1NAT: Analytic LOC: Understanding and applying economic modelsTOP: Circular-flow diagram MSC: Applicative7. ANS: B PTS: 1 DIF: 2 REF: 2-1NAT: Analytic LOC: Understanding and applying economic modelsTOP: Production possibilities frontier MSC: Interpretive8. ANS: C PTS: 1 DIF: 2 REF: 2-1NAT: Analytic LOC: Understanding and applying economic modelsTOP: Production possibilities frontier | Opportunity cost MSC: Interpretive9. ANS: D PTS: 1 DIF: 2 REF: 2-1NAT: Analytic LOC: Understanding and applying economic modelsTOP: Production possibilities frontier MSC: Applicative10. ANS: D PTS: 1 DIF: 3 REF: 2-1NAT: Analytic LOC: Understanding and applying economic modelsTOP: Production possibilities frontier MSC: Analytical11. ANS: B PTS: 1 DIF: 2 REF: 4-2NAT: Analytic LOC: Supply and demand TOP: Market demandMSC: Applicative12. ANS: B PTS: 1 DIF: 2 REF: 4-2NAT: Analytic LOC: Supply and demand TOP: Demand curveMSC: Interpretive13. ANS: A PTS: 1 DIF: 2 REF: 4-2NAT: Analytic LOC: Supply and demand TOP: Demand curveMSC: Applicative14. ANS: A PTS: 1 DIF: 2 REF: 4-2NAT: Analytic LOC: Supply and demand TOP: Determinants of demandMSC: InterpretiveNAT: Analytic LOC: Supply and demand TOP: TastesMSC: Applicative16. ANS: C PTS: 1 DIF: 2 REF: 4-3NAT: Analytic LOC: Supply and demand TOP: Supply curve MSC: Applicative17. ANS: C PTS: 1 DIF: 2 REF: 4-3NAT: Analytic LOC: Supply and demand TOP: Input prices MSC: Applicative18. ANS: D PTS: 1 DIF: 3 REF: 4-4NAT: Analytic LOC: Equilibrium TOP: Surpluses MSC: Analytical 19. ANS: D PTS: 1 DIF: 3 REF: 4-4NAT: Analytic LOC: Equilibrium TOP: Equilibrium MSC: Analytical 20. ANS: B PTS: 1 DIF: 3 REF: 4-4NAT: Analytic LOC: Equilibrium TOP: Equilibrium MSC: Analytical 21. ANS: C PTS: 1 DIF: 2 REF: 23-2NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP MSC: Interpretive22. ANS: A PTS: 1 DIF: 2 REF: 23-2NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP MSC: Applicative23. ANS: C PTS: 1 DIF: 3 REF: 23-2NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP | Intermediate goods MSC: Analytical24. ANS: B PTS: 1 DIF: 3 REF: 23-2NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP | Intermediate goods MSC: Analytical25. ANS: B PTS: 1 DIF: 2 REF: 23-2NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP MSC: Applicative26. ANS: D PTS: 1 DIF: 2 REF: 23-3NAT: Analytic LOC: The study of economics and definitions in economicsTOP: Consumption | GDP MSC: Applicative27. ANS: A PTS: 1 DIF: 3 REF: 23-3NAT: Analytic LOC: The study of economics and definitions in economicsTOP: Consumption | Investment MSC: Analytical28. ANS: B PTS: 1 DIF: 3 REF: 23-3NAT: Analytic LOC: The study of economics and definitions in economicsTOP: Investment | Net exports | GDP MSC: Analytical29. ANS: B PTS: 1 DIF: 3 REF: 23-3NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP MSC: Analytical30. ANS: C PTS: 1 DIF: 3 REF: 23-3NAT: Analytic LOC: The study of economics and definitions in economicsTOP: GDP MSC: Analytical31. ANS: C PTS: 1 DIF: 3 REF: 23-3NAT: Analytic LOC: The study of economics and definitions in economicsTOP: Government purchases MSC: AnalyticalNAT: Analytic LOC: The study of economics and definitions in economics TOP: Nominal GDP | Real GDP MSC: Interpretive33. ANS: C PTS: 1 DIF: 1 REF: 23-4NAT: Analytic LOC: The study of economics and definitions in economics TOP: GDP deflator MSC: Definitional34. ANS: D PTS: 1 DIF: 2 REF: 23-4NAT: Analytic LOC: The study of economics and definitions in economics TOP: Nominal GDP MSC: Applicative35. ANS: B PTS: 1 DIF: 2 REF: 23-4NAT: Analytic LOC: The study of economics and definitions in economics TOP: Real GDP | Price level MSC: Applicative36. ANS: B PTS: 1 DIF: 2 REF: 23-4NAT: Analytic LOC: Unemployment and inflation TOP: Inflation rate MSC: Applicative37. ANS: A PTS: 1 DIF: 2 REF: 24-1NAT: Analytic LOC: Unemployment and inflation TOP: Inflation rate MSC: Interpretive38. ANS: B PTS: 1 DIF: 2 REF: 24-1NAT: Analytic LOC: Unemployment and inflation TOP: Inflation rate MSC: Applicative39. ANS: B PTS: 1 DIF: 2 REF: 24-1NAT: Analytic LOC: The study of economics and definitions in economics TOP: CPI | Price level MSC: Applicative40. ANS: B PTS: 1 DIF: 2 REF: 24-1NAT: Analytic LOC: The study of economics and definitions in economics TOP: Introduction of new goods MSC: Interpretive41. ANS: D PTS: 1 DIF: 2 REF: 26-1NAT: Analytic LOC: The study of economics and definitions in economics TOP: Bonds MSC: Interpretive42. ANS: B PTS: 1 DIF: 2 REF: 26-1NAT: Analytic LOC: The study of economics and definitions in economics TOP: Bonds MSC: Interpretive43. ANS: D PTS: 1 DIF: 2 REF: 26-1NAT: Analytic LOC: The study of economics and definitions in economics TOP: Bonds MSC: Interpretive44. ANS: B PTS: 1 DIF: 2 REF: 26-1NAT: Analytic LOC: The study of economics and definitions in economics TOP: Bonds | Interest rates MSC: Interpretive45. ANS: C PTS: 1 DIF: 2 REF: 26-2NAT: Analytic LOC: The study of economics and definitions in economics TOP: National saving MSC: Applicative46. ANS: C PTS: 1 DIF: 3 REF: 26-2NAT: Analytic LOC: The study of economics and definitions in economics TOP: Private saving | National saving MSC: Applicative47. ANS: C PTS: 1 DIF: 3 REF: 26-2NAT: Analytic LOC: The study of economics and definitions in economics TOP: Private saving | Gross domestic product MSC: Applicative。

日常高频词根120个-3

日常高频词根Root Word1313. range = rank 表示“行，列,顺序”词根range相当于rank的含义,表示“行，顺序”，该词根本身也有“山脉”的意思，而山脉的形状正是一行一行连绵不绝的。

01range---[reɪndʒ] n.山脉；范围，v.变动构成：单词本身为词根例句：It's difficult to find a house in our price range.翻译：在我们的价格范围以内，很难找到房子。

派生词：ranger 突击队员；rangy 宽广的短语：normal range正常范围02arrange--- [əˈreɪndʒ] v.安排；布置；整理构成：ar加强+range行，列；顺序—成行—排列例句：We arranged for a car to collect us from the airport.翻译：我们安排了一辆轿车到机场接我们。

派生词：arrangement 布置；arranged 安排的03rearrange---[ˌriːəˈreɪndʒ] v.重新安排；改变位置构成：re(重新)+ar(加强)+range(行,列)—重新安排例句：Rearrange the letters to form a new word.翻译：重新排列字母，组成另一单词。

派生词：rearrangement 重整拓展词：crooked 不自然的；brace 支架04derange--- [dɪ'reɪndʒ] v.扰乱;精神错乱构成：de毁+range行，列；顺序—破坏顺序—扰乱，引申为使精神错乱例句：Whatever you do, don't let the stress derange owe head.翻译：但无乱咋样，无所不能让压力使得你精神错乱。

派生词：deranged 疯狂的；derangement 精神错乱1414. set = to fix表示“放,置，安置”词根set如同其本身的意思，表示“固定;安置”，看到含有set的单词时,要注意联想到其“放置”的意思。

考研英语中由短横线(hyphen)连接的合成词

考研英语中由短横线（hyphen）连接的合成词作者：杨政（广州新东方国内部）问：08年考研大纲中没有明确指出，但是考试却经常出现的一类单词，86――2006年共出现了576词，平均每年约有28个，是什么词？答：由“-”连接的合成词，其中绝大部分都是复合形容词，还有一小部分为复合名词。

这些词有些出现在题目中，有些出现在选项中，如果不能准确掌握它们的意思，对于理解原文和选择正确的选项将造成巨大障碍。

问：除了认识hyphen连接的复合词，还有别的作用吗？答：除了认识以外，如果掌握了构词方法，可以极大的丰富你的写作词语素材。

例如：我希望坐上“比光速还快的”飞船。

护理行业是“女人统治的”行业。

我需要一些“缓解疼痛的”药物。

“学生写的”作文很有趣。

请问“”中的表达方式，您都会吗？也许你以前需要一个定于从句，但是现在只需要一个hyphen，一切都可以轻松解决。

一．名词＋XX= 形容词，现在分词，过去分词，名词，介词1．名词 + 现在分词job-seeking guide 求职向导peace-loving people 爱好和平的人 noise-making boy 吵闹的男孩mouth-watering baby 留着口水的婴儿 head-scratching puzzlement 让人挠头的难题pain-relieving medication 缓解疼痛的药物 meat-eating animal == carnivore 食肉动物time-consuming 费时的 money-consuming 费钱的 energy consuming 费精力的2．名词 + 过去分词A woman-dominated field 女人统治的领域 student-written compositions 学生写的作文heart-broken story 让人心碎的故事 man-made protein 人造蛋白质3．名词 + 形容词accident-free operations 零事故的手术 Toll-free number 免费电话号码life-long（终生的） world-famous （世界著名的）world-wide （世界范围的）ice-cold （冰冷的）4．名词 + 介词built-in furniture 内嵌式家具 child-like (像小孩似的)5．名词 + 名词Import-export equilibrium 进出口均衡Input-output balance 投入产出平衡health-care system 卫生保健体系intelligence-analysis company 情报分析公司man-machine integration 人机一体化English-language （英国语言的）数量词（名词中的特殊形式）1. 数词 + 名词(单数)one-child policy (独生子女政策/) two-hour talk (两小时的谈话)2. 数词 + 名词(单数) + 形容词three-year-old （三岁的） seven-foot-wide (七英尺的) 8000-meter-long (8000米长的) six-meter-tall (六米高的)3. 数词 + 名词 + ”-ed”one-eyed (独眼的) four-storeyed (四层的) two-faced (两面的) four-footed (四只脚的)二．形容词（或者副词）＋XX= 名词（不适用于副词），名词ed，形容词，现在分词，过去分词1．形容词+名词domestic-relations lawyer 家庭关系律师low-level construction 低水平建设hard-line party 强硬路线的政党first-class/ rate service一流的服务full-time student 全职学生、脱产学生high-class高级的second-hand（二手的） part-time（业余的）mid-term （期中的） final-term（期末的）2. 形容词 + 名词 + “-ed”tight-lipped 很少说话的，守口如瓶的light-hearted轻松愉快的quick-witted 急智的，机敏的good-natured 和蔼的，和善的kind-hearted（好心肠的） cold-blooded （冷血的）warm-hearted（热心肠的） blue-eyed（蓝眼睛的）middle-aged(中年的) red-lipped（红嘴唇的）3. 形容词（副）+现在分词long-standing traditions 长期的传统far-reaching influence 深远的影响ever-changing world 不断变化的世界best-selling novel 最畅销的小说good-looking（长相好看的） ugly-looking（长相丑陋的）easy-looking （长相随和的） tired-looking（面容疲劳的）hard-working （勤奋的） ever-lasting（永恒的）4．形容词/副词+过去分词clear-cut distinctions 鲜明的区别（clear-cut切得很清楚）clean-cut hair-style 整齐的发型（clean-cut切得很干净）ready-made 现成的hotly-contested market old-fashioned 老式的 native-born 本国出生的new-born （新生的）so-called（所谓的）hard-won （来之不易的）well-dressed（衣着好的）newly-built （新建的） recently-built （刚建的）5．形容（副）词 + 形容词dark-blue（深蓝的） light-green（浅绿的）all-round （全面的） red-hot（灼热的）ill, well专题以ill-为前缀的复合形容词，在考研英语中出现了7次，以well-为前缀的出现了24次，这说明这两个词，派生能力很强，我们要重点掌握。

Midterm

1500-1600
Thomas
Weelkes: As Vesta Was Descending (1601)
Shakespeare, Romeo and Juliet (1596) Martin Luther’s ninety-five theses, start
Reformation (1517) Council of Trent (1545-63) Elizabeth I, queen of England (1558-1603) Spanish Armada defeated (1588)
Parallel Organum
Troubadours
•
Troubadours were French musicians who traveled across Europe during the 12th and 13th centuries.
•
They sang mostly love songs.
MIDTERM
MUS 101
35 Questions Multiple choice. 5 listening multiple choice
Listening Listen to the music and chose style or area. Ex: a. Africa b. Japan c. Brazil d. North Pole
Muted Cornett
Psaltery
Sacbut
Serpent
Shawm
Hurdy-Gurdy
Drum or Tambor
Recorder
Viol
Ars Nova
• • • • • •
14th & 15th century France The invention of modern notation The creation of the Ordinary of the Catholic Mass The popularity of the motet The introductory use of phrasing and cadences An awakening to relationship between text and music

期中考试计划英语作文

期中考试计划英语作文Midterm Exam Plan。

The midterm exams are approaching, and it is essential to have a well-structured plan to make the most out of the study time. In this article, we will discuss a comprehensive midterm exam plan that will help you prepare effectively and achieve success. Let's dive in!1. Assess Your Knowledge:Before starting your preparation, it is crucial to assess your current knowledge level. Review the topics covered in the syllabus and identify the areas where you need more focus. This step will help you prioritize your study time and allocate more hours to weaker subjects.2. Create a Study Schedule:Time management is key when preparing for exams. Create a study schedule that allows you to cover all the subjects adequately. Divide your study time into smaller, manageable sessions, and allocate specific hours for each subject. This approach will help you maintain focus and avoid burnout.3. Gather Study Materials:Ensure you have all the necessary study materials, including textbooks, lecture notes, and supplementary resources. Organize your materials in a systematic manner, making it easier to locate and revise specific topics when needed.4. Review Class Notes:Go through your class notes and highlight the main points and key concepts. Condense the information into concise summaries or mind maps, making it easier to revise and remember important details.5. Practice Past Exam Papers:One of the most effective ways to prepare for exams is by practicing past exam papers. Familiarize yourself with the exam format, types of questions, and time constraints. Solving past papers will not only help you gauge your understanding but also improve your time management skills.6. Seek Clarification:If you have any doubts or need clarification on certain topics, don't hesitate to seek help. Approach your teachers, classmates, or join study groups to discuss and understand difficult concepts. Clearing your doubts will strengthen your understanding and boost your confidence.7. Create Flashcards:Utilize flashcards as a study tool to memorize important definitions, formulas, and vocabulary. Write the term or concept on one side and the explanation or definition on the other. Regularly review these flashcards to reinforce your memory.8. Practice Active Learning:Passive reading is not an effective study method. Engage in active learning techniques such as summarizing information in your own words, teaching concepts to others, or participating in group discussions. These activities will enhance your understanding and retention of the material.9. Take Breaks:Studying continuously for long hours can lead to fatigue and decreased productivity. Take short breaks between study sessions to relax your mind and rejuvenate. Engage in activities like stretching, going for a walk, or listening to music to refresh yourself.10. Stay Healthy:Lastly, prioritize your physical and mental well-being. Get enough sleep, eat nutritious meals, and exercise regularly. A healthy body and mind will help you stay focused and perform better during exams.In conclusion, a well-structured midterm exam plan is crucial for effective preparation. Assess your knowledge, create a study schedule, practice past exam papers, seek clarification, and engage in active learning techniques. Remember to take breaks and prioritize your overall well-being. With dedication and proper planning, success in your midterm exams is within reach. Best of luck!。

Midterm Elections 美国中期选举

What is the American Congress?
• Members of both houses are directly elected by voters states. Each state senator 2 election, 50 states, a total of 100 members, elected for a term of 6 years, renewed every two years 1/3. According to the proportion of the population elected congressman States, a total of 435 members, elected for a term of 2 years, after the expiration of the term of all elections.
口语
• 从国家层面上讲，美国国会主要负责制定法律并监督总统行使权力。如果总统所在的政党能够在国会占据多次席位，那么将使得白宫能够更加方便地实施各项政策；而如果另外一个政党占据了国会的多次席次，那么总统在行使权力时将面临很大的牵制；从地方层面来讲，中期选举还将选出各州的州长，而他们将决定各州如何运转。尤其是在美国多个州目前面临经济危机的情况下，州长采取何种政策至关重要。
• 两院议员都由各州选民直接选举产生。参议员每州选2 名，50个州共100名，任期6年，每两年改选1/3。众议员按各州人口比例选出，共435名，任期2年，届满后全部改选。
The purpose of election
• The elections will vote for the following 5 issues: 1、to vote for the 435 House seats. • 2、to elect 1/3 seats of Senate, which means elect 34 senators in 100. • 3、to elect another 3 Senate seats by special election, those seats had been vacated due to some other reasons. 4、to elect the new governors of 37 states. 5、to elect the legislative and administrative institutions of local states or counties.

J2ME自定义字体

字体，文档宽度应为一个字符宽度的 128 倍。例如，如果每一个字符高为 12 像素宽为 10 像素，为容纳所有的 128 个字符，则需要高为 12 宽为 1,280 的图像。
现在有了用于放置对应于 ASCII 代码 0 到 127 的 128 个位置。为了能查明哪个字符放到哪个空位中，可能需要 ASCII 表。请注意前 31 个字符是¡ 控制字符¡ 并且不能看到，可以保留为空白。可以一个像素一个像素地地手动把每一个字符填充到槽中，但使用计算机中的某个字体的字符会更容易一些。确保这个字体是您自己的或有使用许可。我使用的是一种称为 Anonymous 的字体，具有十分清晰的 6-point 显示且免费使用。您可以从 Mark Simonson Studios 下载。使用 Anonymous，我的字体图像看起来是这样的：
public void drawChar( Graphics g, char character, int x, int y, int anchor ) { int clipX = g.getClipX(); int clipY = g.getClipY(); int clipW = g.getClipWidth(); int clipH = g.getClipHeight(); g.setClip( x, y, width, height ); g.drawImage( image, x - width*character, y, anchor ); g.setClip( clipX, clipY, clipW, clipH ); }
ห้องสมุดไป่ตู้
public static CustomFont getFont( String inName, int inStyle, int inSize );

Lecture 6, Midterm_Review STATISTICAL ISSUES IN T

II. Observational Studies Case-control study Cross-sectional study Cohort study Case series Case report
Types of Designs (continued)
III. Other Study Types Meta analyses Experimental study Review Historical manuscript
Types of Study Variables
Continuous variables -- can be measured as precisely as instrumentation permits ➢cholesterol, HDL-cholesterol, age, per-patient change in percent diameter stenosis
Designing a Clinical Research Study
A. Stating Objective: Framing Research Question B. Defining the Study Population C. Selecting the Appropriate Study Design D. Defining the Study Variables E. Rewrite Objectives into Testable Hypotheses F. Selecting the Study Sample and Sample Size Considerations G. Bias and Masking in Clinical Studies H. Determination of Analytic Plan

fa11-midterm

Total /80
2
THIS PAGE INTENTIONALLY LEFT BLANK
NAME:
1. (12 points) Search
3
Consider the search graph shown below. S is the start state and G is the goal state. All edges are bidirectional.
A
D
B
E
ii. h must be admissible and consistent
C G
F
h=0.5
(g) (3 pt) Now suppose that h(F) = 0.5, h(E) = 1.1, and all other heuristic values except h(B) are ﬁxed to zero (as shown on the right). For each of the following parts, indicate the range of values for h(B) that yield an admissible heuristic AND result in the given expansion ordering when using A* graph search. If the given ordering is impossible with an admissible heuristic, write none. Break ties alphabetically. Again, you may assume that h is nonnegative. i. B expanded before E expanded before F

美国大选的一些英文词汇

美国大选的一些词汇1.red states/blue states（红州/蓝州）共和党支持率较高的州在大选地图上用红色标示，蓝色则代表民主党2.Two Americas（两个美国）民主党候选人克里在大选中，指责现任总统布什的经济政策导致美国社会出现严重分化。

克里说他眼里有两个美国：一个富人的美国和一个穷人的美国。

3.Incivility（粗野）毫无疑问，这个单词也与美国大选有直接联系，它是许多美国电视评论员在评价两位总统候选人的三场电视辩论时最常挂在嘴边的一个词。

4.预选会议（Caucus）特指以促进政治上或组织上的变化为目的的聚会。

在美国选举政治中，这个词专指在提名总统候选人的过程中，党的地方活动人士举行的会议。

所谓"分层"预选会议制，是指政党地方活动人士在地方选区会议上选出参加高一级行政区会议的代表，这一级代表再选出参加州一级会议的代表，最后由州级会议代表选出参加本党全国提名代表大会的代表。

预选会议制旨在通过选出支持某一候选人的代表来表明政党在各州内的党员所希望推举的本党总统候选人。

这种做法使决定总统候选人的程序始于基层，因此将总统提名程序民主化。

5.燕尾提举力（Coattails）从旧时绅士长礼服后下摆"燕尾"一词引申而来，在美国政治中，指一位在职民选官员或竞选公职的候选人利用自己的声望给本党其他候选人增加胜选机会的能力──好似让别人受其燕尾之提举，顺势走向胜利。

6.会后弹升（Convention bounce）在共和党或民主党全国代表大会完成总统候选人提名的几天内出现的这位候选人在民意调查中声望上升的现象。

7.辩论（Debate）近年在美国政治中，往往指由电视现场传播的总统或副总统候选人间的辩论；他们通过回答媒体或观众的提问来阐述自己和自己政党的立场观点。

8. 分掌政府（Divided government）通常指白宫由一个政党控制（即总统是这个党的成员），而国会参、众两院中的至少一院由对立派政党控制（即其成员占多数）的局面。

机器学习考试卷 midterm2006

10-701/15-781,Fall2006,Midterm•There are7questions in this exam(11pages including this cover sheet).•Questions are not equally diﬃcult.•If you need more room to work out your answer to a question,use the back of the page and clearly mark on the front of the page if we are to look at what’s on the back.•This exam is open book and open puters,PDAs,cell phones are not allowed.•You have1hour and20minutes.Good luck!Name:Andrew ID:Q Topic Max.Score Score1Conditional Independece,MLE/MAP,Probability122Decision Tree123Neural Network and Regression184Bias-Variance Decomposition125Support Vector Machine126Generative vs.Discriminative Classiﬁer207Learning Theory14Total10011Conditional Independence,MLE/MAP,Probability(12pts)1.(4pts)Show that Pr(X,Y|Z)=Pr(X|Z)Pr(Y|Z)if Pr(X|Y,Z)=Pr(X|Z).2.(4pts)If a data point y follows the Poisson distribution with rate parameterθ,then theprobability of a single observation y isp(y|θ)=θy e−θy!,for y=0,1,2,···.You are given data points y1,···,y n independently drawn from a Poisson distribution with parameterθ.Write down the log-likelihood of the data as a function ofθ.3.(4pts)Suppose that in answering a question in a multiple choice test,an examinee eitherknows the answer,with probability p,or he guesses with probability1−p.Assume that the probability of answering a question correctly is1for an examinee who knows the answer and 1/m for the examinee who guesses,where m is the number of multiple choice alternatives.What is the probability that an examinee knew the answer to a question,given that he has correctly answered it?22Decision Tree(12pts)The following data set will be used to learn a decision tree for predicting whether students are lazy(L)or diligent(D)based on their weight(Normal or Underweight),their eye color(Amber or Violet)and the number of eyes they have(2or3or4).Weight Eye Color Num.Eyes OutputN A2LN V2LN V2LU V3LU V3LU A4DN A4DN V4DU A3DU A3DThe following numbers may be helpful as you answer this problem without using a calculator: log20.1=−3.32,log20.2=−2.32,log20.3=−1.73,log20.4=−1.32,log20.5=−1.*You don’t need to show the derivation for your answers in this problem.1.(3pts)What is the conditional entropy H(EyeColor|W eight=N)?2.(3pts)What attribute would the ID3algorithm choose to use for the root of the tree(nopruning)?3.(4pts)Draw the full decision tree learned for this data(no pruning).4.(2pts)What is the training set error of this unpruned tree?33Neural Network and Regression(18pts)Consider a two-layer neural network to learn a function f:X→Y where X= X1,X2 consists of two attributes.The weights,w1,···,w6,can be arbitrary.There are two possible choices for the function implemented by each unit in this network:•S:signed sigmoid function S(a)=sign[σ(a)−0.5]=sign[11+exp(−a)−0.5]•L:linear function L(a)=c awhere in both cases a=iw i X i1.(4pts)Assign proper activation functions(S or L)to each unit in the following graph so thisneural network simulates a linear regression:Y=β1X1+β2X2.2.(4pts)Assign proper activation functions(S or L)for each unit in the following graph so thisneural network simulates a binary logistic regression classiﬁer:Y=arg max y P(Y=y|X),where P(Y=1|X)=exp(β1X1+β2X2)1+exp(β1X1+β2X2),P(Y=−1|X)=11+exp(β1X1+β2X2).3.(3pts)Following problem3.2,deriveβ1andβ2in terms of w1,···,w6.44.(4pts)Assign proper activation functions(S or L)for each unit in the following graph so thisneural network simulates a boosting classiﬁer which combines two logistic regression classiﬁers, f1:X→Y1and f2:X→Y2,to produce itsﬁnal prediction:Y=sign[α1Y1+α2Y2].Use the same deﬁnition in problem3.2for f1and f2.5.(3pts)Following problem3.4,deriveα1andα2in terms of w1,···,w6.54Bias-Variance Decomposition(12pts)1.(6pts)Suppose you have regression data generated by a polynomial of degree3.Characterizethe bias-variance of the estimates of the following models on the data with respect to the true model by circling the appropriate entry.Bias VarianceLinear regression low/high low/highPolynomial regression with degree3low/high low/highPolynomial regression with degree10low/high low/high2.Let Y=f(X)+ ,where has mean zero and varianceσ2 .In k-nearest neighbor(kNN)regression,the prediction of Y at point x0is given by the average of the values Y at the k neighbors closest to x0.(a)(2pts)Denote the -nearest neighbor to x0by x( )and its corresponding Y value byy( ).Write the predictionˆf(x0)of the kNN regression for x0in terms of y( ),1≤ ≤k.(b)(2pts)What is the behavior of the bias as k increases?(c)(2pts)What is the behavior of the variance as k increases?65Support Vector Machine(12pts)Consider a supervised learning problem in which the training examples are points in2-dimensional space.The positive examples are(1,1)and(−1,−1).The negative examples are(1,−1)and (−1,1).1.(1pts)Are the positive examples linearly separable from the negative examples in the originalspace?2.(4pts)Consider the feature transformationφ(x)=[1,x1,x2,x1x2],where x1and x2are,respectively,theﬁrst and second coordinates of a generic example x.The prediction function is y(x)=w T∗φ(x)in this feature space.Give the coeﬃcients,w,of a maximum-margin decision surface separating the positive examples from the negative examples.(You should be able to do this by inspection,without any signiﬁcant computation.)3.(3pts)Add one training example to the graph so the totalﬁve examples can no longer belinearly separated in the feature spaceφ(x)deﬁned in problem5.2.4.(4pts)What kernel K(x,x )does this feature transformationφcorrespond to?76Generative vs.Discriminative Classiﬁer(20pts)Consider the binary classiﬁcation problem where class label Y∈{0,1}and each training example X has2binary attributes X1,X2∈{0,1}.In this problem,we will always assume X1and X2are conditional independent given Y,that the class priors are P(Y=0)=P(Y=1)=0.5,and that the conditional probabilities are as follows:P(X1|Y)X1=0X1=1 Y=00.70.3 Y=10.20.8P(X2|Y)X2=0X2=1 Y=00.90.1 Y=10.50.5The expected error rate is the probability that a classiﬁer provides an incorrect prediction for an observation:if Y is the true label,letˆY(X1,X2)be the predicted class label,then the expected error rate isP DY=1−ˆY(X1,X2)=1X1=01X2=0P DX1,X2,Y=1−ˆY(X1,X2).Note that we use the subscript D to emphasize that the probabilities are computed under the true distribution of the data.*You don’t need to show all the derivation for your answers in this problem.1.(4pts)Write down the na¨ıve Bayes prediction for all the4possible conﬁgurations of X1,X2.The following table would help you to complete this problem.X1X2P(X1,X2,Y=0)P(X1,X2,Y=1)ˆY(X1,X2)000110112.(4pts)Compute the expected error rate of this na¨ıve Bayes classiﬁer which predicts Y givenboth of the attributes{X1,X2}.Assume that the classiﬁer is learned with inﬁnite training data.83.(4pts)Which of the following two has a smaller expected error rate?•the na¨ıve Bayes classiﬁer which predicts Y given X1only•the na¨ıve Bayes classiﬁer which predicts Y given X2only4.(4pts)Now,suppose that we create a new attribute X3,which is a deterministic copy of X2.What is the expected error rate of the na¨ıve Bayes which predicts Y given all the attributes (X1,X2,X3)now?Assume that the classiﬁer is learned with inﬁnite training data.5.(4pts)Explain what is happening with na¨ıve Bayes in problem6.4?Does logistic regressionsuﬀer from the same problem?Why?97Learning Theory(14pts)You read in the paper that the famous bird migration website,Netﬂocks,is oﬀering a$1M prize for accurately recommending movies about penguins.Furthermore,it is providing a training data set containing100,000,000labeled training examples.Each training example consists of a set of100real-valued features describing a movie,along with a boolean label indicating whether to recommend this movie to a person.You determine that the$1M can be yours if you can train a linear Support Vector Machine with a true accuracy of98%.Of course you understand that PAC learning theory provides only probabilistic bounds,so you decide to enter only if you can prove you have at least a0.9probability of achieving an accuracy of98%.1.(8pts)Can you use PAC learning theory to decide whether you can meet your performanceobjective?If yes,give an expression for the number of training examples suﬃcient to meet your performance objective.If not,explain why not,then provide the minimum set of addi-tional assumptions needed so that PAC learning theory can be applied,and give an expression of the number of training examples suﬃcient under your assumptions.(you may leave your expression as an unsolved arithmetic expression,but it should contain only constants-no variables).102.(3pts)Consider the PAC-style statement“we can achieve true accuracy of at least98%withprobability0.9.”What is the meaning of“with probability0.9”?Answer this by describinga randomized experiment which you could perform repeatedly to test whether the statementis true.3.(3pts)Your friend already has a private dataset of100,000,000labeled movies,so she will endup with twice as much training data as you.You train using the Netﬂocks data to producea classiﬁer h1.She uses the same learning algorithm,but trains with twice as much data toproduce her output hypothesis,h2.You are interested in how well the training errors of h1 and h2predict their true errors.Consider the ratioerror train(h1)−error true(h1)error train(h2)−error true(h2)Which of these is the most likely value for this ratio?Circle the answer and give a one-sentence explanation.4,2,√2,1,−1,1√2,12,14*Any resemblance to real persons,animals,or organizations,living or dead,is purely coincidental.11。

Midterm 1 practice question solutions

4-24(20-25 min.)Job costing, budgeted rates, unit costs.1. Budgeted MOH Rate = Budgeted Manufacturing Overhead Costs Budgeted Direct Labour Hours-= $632,000/32,000= $19.75 per direct labour-hourJob X905:Direct Materials $13,200Direct Labour $10,120Overhead Allocated–460 hours @ $19.75 $9,085Total $32,405# of units 600Unit Cost $54.01# of Direct Labour-Hours on Job X905 = Direct Labour Costs/Hourly Rate= $10,120/$22 = 460 hours2.To achieve a margin of 25%, the selling price must be $72.01 (rounded down)USP – Unit Cost = 0.25USPUSP –$54.01 = 0.25USP0.75USP = $54.01USP = $54.01/0.75 = $72.01 (rounded down) 3.Under- or overallocated overhead = Actual Overhead – Allocated OverheadUnder- or overallocated overhead = $656,125 – ($19.75 ⨯ 34,100)Under- or overallocated overhead = $656,125 – $673,475Overhead is overallocated by $17,350.5-37(30–40 min.) Activity-based costing, merchandising.1. GeneralSupermarket Chains DrugstoreChainsMom-and-PopSingleStores TotalRevenue $3,708,000 $3,150,000 $1,980,000 $8,838,000Cost of goods sold 3,600,000 3,000,000 1,800,000 8,400,000Gross margin $ 108,000 $ 150,000 $ 180,000 $ 438,000Other operating costs 301,080 Operating income $ 136,920Gross margin % 2.91% 4.76% 9.09%The gross margin of Pharmacare Inc. was 4.96% (= $438,000 ÷ $8,838,000). The operating income margin of Pharmacare Inc. was 1.55% (= $136,920 ÷ $8,838,000).1.The per-unit cost driver rates are:1. Customer purchase order processing,$80,000 ÷ 2,000 (140 + 360 + 1,500) orders = $40 per order2. Line item ordering,$63,840 ÷ 21,280 (1,960 + 4,320 + 15,000) line items = $3 per line item3. Store delivery,$71,000 ÷ 1,480 (120 + 360 + 1,000) deliveries = $47.973 per delivery4. Cartons shipped,$76,000 ÷ 76,000 (36,000 + 24,000 + 16,000) cartons = $1 per carton5. Shelf-stocking,$10,240 ÷ 640 (360 + 180 + 100) hours = $16 per hour2.The activity-based costing of each distribution market for August 2015 is:GeneralSupermarket Chains DrugstoreChainsMom-and-PopSingleStores Total1. Customer purchase orderprocessing($40 ⨯ 140; 360; 1,500) $ 5,600 $14,400 $ 60,000 $ 80,000 2. Line item ordering($3 ⨯ 1,960; 4,320; 15,000) 5,880 12,960 45,000 63 ,840 3. Store delivery($47.973 ⨯ 120; 360; 1,000) 5,757 17,270 47,973 71,000 4. Cartons shipped($1 ⨯ 36,000; 24,000; 16,000) 36,000 24,000 16,000 76,000 5. Shelf-stocking($16 ⨯ 360; 180; 100) 5,760 2,880 1,600 10,240$58,997 $71,510 $170,573 $301,080The revised operating income statement is:General Mom-and-PopSupermarket Drugstore SingleChains Chains Stores Total Revenue $3,708,000 $3,150,000 $1,980,000 $8,838,000Cost of goods sold 3,600,000 3,000,000 1,800,000 8,400,000 Gross margin 108,000 150,000 180,000 438,000 Operating costs 58,997 71,510 170,573 301,080 Operating income $ 49,003 $ 78,490 $ 9,427 $ 136,920Operating income margin 1.32% 2.49% 0.48% 1.55%4. The ranking of the three markets are:Using Gross Margin Using Operating Income1. Mom-and-Pop Single Stores 9.09% 1. Drugstore Chains2.49%2. Drugstore Chains 4.76% 2. General Supermarket Chains 1.32%3. General Supermarket Chains 2.91% 3. Mom-and-Pop Single Stores 0.48%The activity-based analysis of costs highlights how the Mom-and-Pop Single Stores use a larger amount of Pharmacare’s resources per revenue dollar than do the other two markets. The ratio of the operating costs to revenue across the three markets is:General Supermarket Chains 1.59% ($58,997 ÷ $3,708,000)Drugstore Chains 2.27% ($71,510 ÷ $3,150,000)Mom-and-Pop Single Stores 8.61% ($170,573 ÷ $1,980,000)This is a class ic illustration of the maxim that “all revenue dollars are not created equal.” The analysis indicates that the Mom-and-Pop Single Stores are the least profitable market. Pharmacare should work to increase profits in this market through: (1) a possible surcharge, (2) decreasing the number of orders,(3) offering discounts for quantity purchases, etc.Other issues for Pharmacare to consider include:a. Choosing the appropriate cost drivers for each area. The problem gives acost driver for each chosen activity area. However, it is likely that overtime further refinements in cost drivers would occur. For example, not allstore deliveries are equally easy to make, depending on parkingavailability, accessibility of the storage/shelf space to the delivery point,etc. Similarly, not all cartons are equally easy to deliver—their weight,size, or likely breakage component are factors that can vary across cartontypes.b. Developing a reliable data base on the chosen cost drivers. For someitems, such as the number of orders and the number of line items, thisinformation likely would be available in machine readable form at a highlevel of accuracy. Unless the delivery personnel have hand-heldcomputers that they use in a systematic way, estimates of shelf-stockingtime are likely to be unreliable. Advances in information technology likelywill reduce problems in this area over time.c. Deciding how to handle costs that may be common across severalactivities. For example, (3) store delivery and (4) cartons shipped to storeshave the common cost of the same trip. Some organizations may treat (3)as the primary activity and attribute only incremental costs to (4).Similarly, (1) order processing and (2) line item ordering may havecommon costs.d. Behavioural factors are likely to be a challenge to Flair. He must now tellthose salespeople who specialize in Mom-and-Pop accounts that theyhave been less profitable than previously thought.6-24(15-20 min.)Revenue, production, and purchases budget.1. 985,000 motorcycles ⨯ 505,000 yen = 497,425,000,000 yen2. Budgeted sales (units) 985,000Add target ending finished goods inventory 115,000Total requirements 1,100,000Deduct beginning finished goods inventory 152,000Units to be produced 948,0003. Direct materials to be used in production, 948,000 ⨯ 2 1,896,000Add target ending direct materials inventory 28,000Total requirements 1,924,000Deduct beginning direct materials inventory 19,000Direct materials to be purchased 1,905,000Cost per wheel in yen 21,300Direct materials purchase cost in yen 40,576,500,000Note the relatively small inventory of wheels. In Japan, suppliers tend to be located very close to the major manufacturer. Inventories are controlled by just-in-time (JIT) and similar systems. Indeed, some direct materials inventories are almost nonexistent.8-16(20 min.) Variable manufacturing overhead, variance analysis.1. Variable Manufacturing Overhead Variance Analysis for Young Clothing forJune 2015Actual CostsIncurredActual Input Qty. × Actual Rate(1) Actual Input Qty.× Budgeted Rate(2)Flexible Budget:Budgeted Input Qty.Allowed forActual Output× Budgeted Rate(3)Allocated:Budgeted Input Qty.Allowed forActual Output× Budgeted Rate(4)1(4,536 × $11.50) $52,164 (4,536 × $12)$54,432(4 × 1,080 × $12)$51,840(4 × 1,080 × $12)$51,8402. Young had a favourable rate variance of $2,268 because the actual variableoverhead rate was $11.50 per direct manufacturing labour-hour versus $12 budgeted. It had an unfavourable efficiency variance of $2,592 U because each suit averaged 4.2 labour-hours (4,536 hours ÷ 1,080 suits) versus 4.0 budgeted labour-hours.$324 U17-30 (20-25 min.) Standard-costing method, assigning costs.1.SOLUTION EXHIBIT 17-30ASteps 1 and 2: Summarize Output in Physical Units and Compute Output in Equivalent Units; Standard Costing Method of Process Costing for Bucky’s Boxes for July 2015(Step 1) (Step 2)Equivalent UnitsFlow of ProductionPhysical Units Direct Materials Conversion Costs Work in process, beginning (given) Started during current period (given) To account for185,000 465,000 650,000 (work done before current period) Completed and transferred out during current period: From beginning work in process §185,000 ⨯ (100% - 100%); 185,000 ⨯ (100% – 25%) 185,000 0138,750Started and completed327,000 100%, 327,000 100% 327,000† 327,000327,000Work in process, ending* (given) 138,000 100%; 138,000 80% 138,000 _______ 138,000 110,400 Accounted for650,000 _______ _______ Work done in current period only 465,000 576,150§Degree of completion in this department: direct materials, 100%; conversion costs, 25%.†512,000 physical units completed and transferred out minus 185,000 physical units completed and transferred out from beginning work-in-process inventory.*Degree of completion in this department: direct materials, 100%; conversion costs, 80%.⨯⨯⨯⨯2.SOLUTION EXHIBIT 17-30BSteps 3, 4, and 5: Summarize Total Costs to Account For, Compute Cost per Equivalent Unit, and Assign Total Costs to Units Completed and to Units in Ending Work in Process; Standard Costing Method of Process Costing for Bucky’s Boxes for July 2015TotalProduction CostsDirectMaterialsConversionCosts(Step 3) Work in process, beginning (given) $ 337,625 $240,500 + $ 97,125 Costs added in current period at standardcosts1,814,415 (465,000 ⨯ $1.30) + (576,150 ⨯ $2.10) Total costs to account for $2,152,040 $845,000 + $1,307,040 (Step 4) Standard cost per equivalent unit (given) $ 1.30 $ 2.10 (Step 5) Assignment of costs at standard costs:Completed and transferred out (512,000 units):Work in process, beginning (185,000 units) Costs added to beg. work in process in current periodTotal from beginning inventory $ 337,625291,375629,000$240,500 + $97,125(0* ⨯ $1.30) + (138,750* ⨯ $2.10)Started and completed (327,000 units) Total costs of units transferred out 1,111,8001,740,800(327,000†⨯ $1.30) + (327,000† ⨯ $2.10)Work in process, ending (138,000 units) 411,240 (138,000# ⨯ $1.30) + (110,400# ⨯ $2.10) Total costs accounted for $2,152,040 $845,000 + $1,307,040Summary of variances for current performance: Costs added in current period at standard costs (see Step 3 above)Actual costs incurred (given)Variance $604,500607,500$ 3,000 U$1,209,9151,207,415$ 2,500 F*Equivalent units to complete beginning work in process from Solution Exhibit 17-30A, Step 2.†Equivalent units started and completed from Solution Exhibit 17-30A, Step 2.#Equivalent units in ending work in process from Solution Exhibit 17-30A, Step 2.PROBLEMS17-31(25 min.) Weighted-average method.1. Since direct materials are added at the beginning of the assembly process, theunits in this department must be 100% complete with respect to direct materials.Solution Exhibit 17-31A shows equivalent units of work done to date:Direct materials 25,000 equivalent unitsConversion costs 24,250 equivalent unitsSOLUTION EXHIBIT 17-31ASteps 1 and 2: Summarize Output in Physical Units and Compute Output in Equivalent Units; Weighted-Average Method of Process Costing, Assembly Department of Larsen Corp., for October 2015.(Step 1) (Step 2)Equivalent UnitsPhysical Direct Conversion Flow of Production Units Materials Costs Work in process, beginning (given) 5,000Started during current period (given) 20,000To account for 25,000Completed and transferred outduring current period 22,500 22,500 22,500Work in process, ending* (given) 2,5002,500 ⨯ 100%; 2,500 ⨯ 70% 2,500 1,750 Accounted for 25,000Work done to date 25,000 24,250*Degree of completion in this department: direct materials, 100%; conversion costs, 70%.2. &3. Solution Exhibit 17-31B summarizes the total assembly department costs forOctober 2015, calculates cost per equivalent unit of work done to date, and assigns these costs to units completed (and transferred out) and to units in ending work in process using the weighted-average method.SOLUTION EXHIBIT 17-31BSteps 3, 4, and 5: Summarize Total Costs to Account For, Compute Cost per Equivalent Unit, and Assign Total Costs to Units Completed and to Units in Ending Work in Process; Weighted-Average Method of Process Costing, Assembly Department of Larsen Corp., for October 2015TotalProduction CostsDirectMaterialsConversionCosts(Step 3) Work in process, beginning (given) $1,652,750 $1,250,000 $ 402,750 Costs added in current period (given) 6,837,500 4,500,000 2,337,500 Total costs to account for $8,490,250 $5,750,000 $2,740,250 (Step 4) Costs incurred to date $5,750,000 $2,740,250 Divide by equivalent units of work done to date(Solution Exhibit 17-31A) ÷ 25,000 ÷ 24,250 Cost per equivalent unit of work done to date $ 230 $ 113 (Step 5) Assignment of costs:Completed and transferred out (22,500units)$7,717,500 (22,500* ⨯ $230) + (22,500*⨯ $113) Work in process, ending (2,500 units) 772,750 (2,500† ⨯ $230) + (1,750†⨯ $113)Total costs accounted for $8,490,250 $5,750,000 + $2,740,250*Equivalent units completed and transferred out from Solution Exhibit 17-31A, Step 2. †Equivalent units in work in process, ending from Solution Exhibit 17-31A, Step 2.。

mid词根

mid词根Mid词根在英语中，很多词都包含有一些类似的词根，这些词根在很大程度上决定了单词的含义。

今天，我们讲述的是mid词根，它是用来表示“中间”、“中央”这样的概念的。

下面将按照词性划分来详细介绍mid词根的应用。

名词形式1. Midterm：中期考试，意为在学期中进行的考试，旨在测试学生的知识掌握程度。

2. Midnight：午夜，意思是夜晚的正中时刻，通常是12点。

3. Midpoint：中点，表示线段或曲线的平分点，也可以是区间的中间点。

4. Midlife：中年，表示一个人生命的中期。

5. Midway：中途，表示在一段旅程或竞赛中到达的中间位置，也可以是一个游乐园的中间区域。

动词形式1. Midst：位于中间，通常是指在某个集体或环境中心部分的位置。

2. Midair：在空中，表示飞行或跳动时的状态。

3. Midrange：处于中等范围，指数值或价值处于中等水平。

4. Midway：到达中途，指到达旅程或竞争的中间位置。

形容词形式1. Midway：中途的，表示位于一段旅程或竞赛中心部分的。

2. Midsize：中等尺寸的，表示处于较小和较大之间的尺寸。

3. Midyear：年中的，表示一年的中间部分。

4. Midsection：中心部分的，指分裂物品中的中间部分，例如某个果实或是人体的躯干部分。

习惯用语1. In the midst of：在……的中心部分，表示在某一事物的中心部分。

例如：In the midst of the storm，表示在暴风雨中心。

2. Midlife crisis：中年危机，指中年时期的生活危机，通常表现为个人价值观的混乱和对未来缺乏方向感。

3. Midas touch：米达斯之手，意为拥有神奇能力，在商业或金融上特别成功。

4. Midweek：工作日的中间，特别是周三这一天。

结语这些词汇都以mid词根为基础，给我们提供了很多表示中间位置或中介状态的词汇和习惯用语。

practice-midterm

CS229Practice Midterm 1CS 229,Autumn 2007Practice Midterm1.[13points]Generalized Linear ModelsRecall that generalized linear models assume that the response variable y (conditioned on x )is distributed according to a member of the exponential family:P (y ;η)=b (y )exp(ηT (y )−a (η)),where η=θT x .For this problem,we will assume η∈R .(a)[10points]Given a training set {(x (i ),y (i ))}m i =1,the loglikelihood is given byℓ(θ)=m i =1log p (y (i )|x (i );θ).Give a set conditions on b (y ),T (y ),and a (η)which ensure that the loglikelihood is a concave function of θ(and thus has a unique maximum).Your conditions must be reasonable,and should be as weak as possible.(E.g.,the answer “any b (y ),T (y ),and a (η)so that ℓ(θ)is concave”is not reasonable.Similarly,overly narrow conditions,including ones that apply only to speciﬁc GLIMs,are also not reasonable.)(b)[3points]When the response variable is distributed according to a Normal distribu-tion (with unit variance),we have b (y )=12πe −y 22.Verifythat the condition(s)you gave in part (a)hold for this setting.2.[15points]Bayesian linear regressionConsider Bayesian linear regression using a Gaussian prior on the parameters θ∈R n +1.Thus,in our prior,θ∼N ( 0,τ2I n ),where τ2∈R ,and I n +1is the n +1-by-n +1identity matrix.Also let the conditional distribution of y (i )given x (i )and θbe N (θT x (i ),σ2),as in our usual linear least-squares model.1Let a set of m IID training examples be given (with x (i )∈R n +1).Recall that the MAP estimate of the parameters θis given by:θMAP =arg max θ m i =1p (y (i )|x (i ),θ) p (θ)Find,in closed form,the MAP estimate of the parameters θ.For this problem,you should treat τ2and σ2as ﬁxed,known,constants.[Hint:Your solution should involve deriving something that looks a bit like the Normal equations.]CS229Practice Midterm23.[18points]KernelsIn this problem,you will prove that certain functions K give valid kernels.Be careful to justify every step in your proofs.Speciﬁcally,if you use a result proved either in the lecture notes or homeworks,be careful to state exactly which result you’re using.(a)[8points]Let K(x,z)be a valid(Mercer)kernel over R n×R n.Consider the functiongiven byK e(x,z)=exp(K(x,z)).Show that K e is a valid kernel.[Hint:There are many ways of proving this result,but you mightﬁnd the following two facts useful:(i)The Taylor expansion of e x isgiven by e x= ∞j=01σ2,whereσ2>0is someﬁxed,positive constant.We said in class that this is a validkernel,but did not prove it.Prove that the Gaussian kernel is indeed a valid kernel.[Hint:The following fact may be useful.||x−z||2=||x||2−2x T z+||z||2.]4.[18points]One-class SVMGiven an unlabeled set of examples{x(1),...,x(m)}the one-class SVM algorithm tries to ﬁnd a direction w that maximally separates the data from the origin.2More precisely,it solves the(primal)optimization problem:1min w2This turns out to be useful for anomaly detection,but I assume you already have enough to keep you entertained for the2h15min of the midterm,and thus wouldn’t want to read about it here.See the midterm solutions for details.CS229Practice Midterm3 that(with high probability),after some initial set of N tosses,the running estimate fromthat point on will always be accurate and never deviate too much from the true value.More formally,let X i∼Bernoulli(φ)be IID random variables.Letˆφn be our estimate for φafter n observations:ˆφn =1γ2log(11−exp(−2γ2))=O(log(1CS229Practice Midterm4(d)[5points]Let f:R n→R be deﬁned according to f(x)=x⊤Ax+b⊤x+c,whereA is symmetric positive deﬁnite.Suppose we use Newton’s method to minimize f.Show that Newton’s method willﬁnd the optimum in exactly one iteration.You mayassume that Newton’s method is initialized with 0.(e)[5points]Consider binary classiﬁcation,and let the input domain be X={0,1}n,i.e.,the space of all n-dimensional bit vectors.Thus,each sample x has n binary-valued features.Let H n be the class of all boolean functions over the input space.What is|H n|and V C(H n)?(f)[5points]Suppose anℓ1-regularized SVM(with regularization parameter C>0)istrained on a dataset that is linearly separable.Because the data is linearly separable,to minimize the primal objective,the SVM algorithm will set all the slack variablesto zero.Thus,the weight vector w obtained will be the same no matter what reg-ularization parameter C is used(so long as it is strictly bigger than zero).True orfalse?(g)[5points]Consider using hold-out cross validation(using70%of the data for training,30%for hold-out CV)to select the bandwidth parameterτfor locally weighted linearregression.As the number of training examples m increases,would you expect thevalue ofτselected by the algorithm to generally become larger,smaller,or neither ofthe above?For this problem,assume that(the expected value of)y is a non-linearfunction of x.(h)[5points]Consider a feature selection problem in which the mutual informationMI(x i,y)=0for all features x i.Also for every subset of features S i={x i1,···,x ik}of size<n/2we have MI(S i,y)=0.3However there is a subset S∗of size exactly n/2 such that MI(S∗,y)=1.I.e.this subset of features allows us to predict y correctly. Of the three feature selection algorithms listed below,which one do you expect to work best on this dataset?i.Forward Search.ii.Backward Search.iii.Filtering using mutual information MI(x i,y).iv.All three are expected to perform reasonably well.。