midterm09

# midterm09 - Name CS573 STAT598M Midterm Spring 2009 This is...

This preview shows pages 1–6. Sign up to view the full content.

Name: ————————————— CS573 / STAT598M Midterm: Spring 2009 This is a closed-book, closed-notes exam. Non-programmable calculators are allowed for probability calculations. There are 12 pages including the cover page. The total number of points for the exam is 60. Note the point value of each question and allocate your time accordingly. Read each question carefully and show your work. Question Score 1 2 3 4 5 6 7 Total 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
1 Data mining components (8 pts) Read the excerpts from Mining Citizen Science Data to Predict Abundance of Wild Bird Species by R. Caruana, M. Elhawary, A. Munson, M. Riedewald, D. Sorokina, D. Fink, W. Hochachka, S. Kelling, KDD, 2006 on pages 11-12. 1. Describe the data mining task. 2. Describe the data representation. 3. Describe the knowledge representation. 4. Describe the learning algorithm (both search and evaluation). 2
2 Short Questions (12 pts, 2 pts each) The following short questions should be answered with at most two sentences, and/or a picture. For the (true/false) questions, answer true or false. If you answer true, provide a short justication, if false explain why or provide a small counterexample. 1. True or False. Consider a continuous probability distribution with density f () that is nonzero everywhere. The probability of a value x is equal to f ( x ). 2. True or False. MAP estimates are less prone to overtting than MLE. 3. Consider a classiﬁcation problem with two classes and n binary attributes. How many pa- rameters would you need to learn with a Naive Bayes classiﬁer? How many parameters would you need to learn a model of the full joint distribution? 4. In n -fold cross-validation each data point belongs to exactly one test fold, so the test folds are independent. Given that the data in test folds i and j are independent, are e i and e j , the error estimates on test folds i and j , also independent? 3

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
5. Give one similarity and one diﬀerence between feature selection and PCA. 6. You are a reviewer for the International Conference on Automatically Mining Nuggets from Data, and you read papers with the following experimental setups. Would you accept or reject each paper? Provide a one sentence justication. (This conference has short reviews.) accept/reject “My algorithm is better than yours. Look at the training error rates!” accept/reject “My algorithm is better than yours. Look at the test error rates! (Foot- note: reported results for λ = 1 . 789489345672120002.)” accept/reject “My algorithm is better than yours. Look at the test error rates! (Foot- note: reported results for best value of λ .)” accept/reject “My algorithm is better than yours. Look at the test error rates! (Foot- note: reported results for best value of λ , chosen with 10-fold cross validation.)” 4
3 Decision trees (12 pts) 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

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 04/08/2012 for the course CS 573 taught by Professor Staff during the Spring '08 term at Purdue.

### Page1 / 12

midterm09 - Name CS573 STAT598M Midterm Spring 2009 This is...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online