10-601 Machine Learning: Homework Assignment 3:
Solution to Purnas question
Professor Tom Mitchell
Carnegie Mellon University
February 3, 2009
The assignment is due at 1:30pm (beginning of class) on Wednesday, February 18, 2009.
Submit writeups to Probl

10-601 Machine Learning, Fall 2012
Homework 3
Instructors: Tom Mitchell, Ziv Bar-Joseph
TA in charge: Mehdi Samadi
email: [email protected]
Due: Monday October 15, 2012 by 4pm
Instructions There are 4 questions on this assignment no programming. Please h

10-601 Machine Learning: Homework Assignment 2
Professor Tom Mitchell
Carnegie Mellon University
January 21, 2009
The assignment is due at 1:30pm (beginning of class) on Monday, February 2, 2009.
Submit writeups to Problem 1 and Problem 2 separately wit

10-601 Machine Learning, Fall 2012
Homework 2
Instructors: Tom Mitchell, Ziv Bar-Joseph
TA in charge: Selen Uguroglu
email: [email protected]
SOLUTIONS
1
Naive Bayes, 20 points
Problem 1. Basic concepts, 10 points
Naive Bayes reduces the number of par

10-601 Machine Learning: Homework Assignment 2 Solutions
Professor Tom Mitchell
Carnegie Mellon University
January 21, 2009
The assignment is due at 1:30pm (beginning of class) on Monday, February 2, 2009.
Submit writeups to Problem 1 and Problem 2 sepa

10-601 Machine Learning, Fall 2009: Homework 5
Due: December,2nd , 10:30 am
Instructions There are 4 questions on this assignment worth a total of 160 points. Please hand in a hard
copy at the beginning of the class. Please print your code and attach it t

Hidden Markov Models
Machine Learning 10-601
April 15, 2009
Tom M. Mitchell
Machine Learning Department
Carnegie Mellon University
With thanks to Prof. Carlos Guestrin for some of these slides
Handwriting recognition
Character recognition, e.g., logistic

10-601: HW4 Problem 1 Solution
1
D-Separation [Andy: 21 points]
Which of the following statements are true with respect to the following graphical model, regardless
of the conditional probability distributions? If false, explain why by giving a path which

10-601 Machine Learning, Fall 2009: Homework 2
Due: Wednesday, September 16nd , 10:30 am
Instructions There are 4 questions on this assignment worth the total of 100 points. Please hand in a
hard copy at the beginning of the class. Refer to the webpage fo

10-601 Machine Learning, Fall 2009: Homework 3
Due: Wednesday, October 7th , 10:30 am
Instructions There are 3 questions on this assignment worth the total of 140 points. Please hand in a
hard copy at the beginning of the class. Refer to the webpage for p

10-601 Machine Learning, Fall 2009: Homework 4
Due: Wednesday, October 28th , 10:30 am
Instructions There are 2 questions on this assignment worth a total of 100 points. Please hand in a hard
copy at the beginning of the class. Please print your code and

10-601 Machine Learning, Fall 2009: Homework 2 Solutions
Due: Wednesday, September 16nd , 10:30 am
Instructions There are 4 questions on this assignment worth the total of 100 points. Please hand in a
hard copy at the beginning of the class. Refer to the

10-601 Machine Learning, Fall 2009: Homework 4
Due: Wednesday, October 28th , 10:30 am
Instructions There are 2 questions on this assignment worth a total of 100 points. Please hand in a hard
copy at the beginning of the class. Please print your code and

10-601 Machine Learning, Fall 2009: Homework 3
Due: Wednesday, October 7th , 10:30 am
Instructions There are 3 questions on this assignment worth the total of 140 points. Please hand in a
hard copy at the beginning of the class. Refer to the webpage for p

10-701: Machine Learning
Midterm Solutions
March 21, 2012
Name:
Andrew ID:
Instructions:
Make sure that your exam has 15 pages and is not missing any sheets,
then write your full name and Andrew ID on this page (and all others
if you want to be safe).
W

Reducing Data Dimension
Recommended readings (available on class website):
A Tutorial on PCA, J. Schlens
Wall et al., 2003
Machine Learning 10-601
April 8, 2009
Tom M. Mitchell
Machine Learning Department
Carnegie Mellon University
Outline
Unsupervised

10-601 Machine Learning: Homework Assignment 5
Professor Tom Mitchell
Carnegie Mellon University
March 30, 2009
The assignment is due at 1:30pm (beginning of class) on Monday, April 6, 2009.
Submit writeups to the two problems separately with your name

10-601 Recitation #1
Function Approximation, Decision
Trees, and Overfitting
September 14th, 2011
Shing-hon Lau
Office hours: Friday 3-4 PM
Agenda
Administrivia
Function
Approximation
Decision
Trees
Overfitting
Administrivia
Course
10601/)
website (w

10601 Machine Learning
September 21, 2011
Mladen Kolar
Announcements
Fill in a survey at
http:/www.surveymonkey.com/s/J7Q5JHL
Recitations
Wed 6 7pm (this time) or
Fri 4 5 pm
Homework 1 is due on Monday, noon
Outline
Probability overview
Maximum lik

10-601 Recitation #4
Gaussian Naive Bayes
and Logistic Regression
October 5th, 2011
Shing-hon Lau
Office hours: Friday 3-4 PM
Agenda
HW #2 due tomorrow 5 PM
Submit written copy and post code to Blackboard
Gaussian Naive Bayes
Logistic Regression
Gradient

10-601 Machine Learning
HW4, Section 2. Inference Solutions
Thanks to Michael D. George for providing his solution.
March 2, 2009
2
2.1
P (O = t, W = t, H = t, S = f, F = f ) = P (O = t)P (H = t|O = t, W = t)P (W = t)P (S = f |W = t)P (F = f |S = f )
= 0.

10-601 Machine Learning: Homework Assignment 1 - Solution
* Implement the Basic Decision Tree Learning Algorithm *
Implement the ID3 decision tree learning algorithm described in
post-pruning). You may use any programming language you like.
easy, your pro

10-601 Machine Learning, Fall 2009: Homework 1
Due: Wednesday, September 2nd , 10:30 am
Instructions There are 5 questions on this assignment worth the total of 120 points. The last question
involves some basic programming. Please hand in a hard copy at t

10-601 Machine Learning: Homework Assignment 4
Professor Tom Mitchell
Carnegie Mellon University
February 18, 2009
The assignment is due at 1:30pm (beginning of class) on Monday, March 2, 2009.
Submit writeups to the three problems separately with your

Feature Selection
Regularization
Regression
Machine Learning 10-601
Feb 11, 2009
Tom M. Mitchell
Machine Learning Department
Carnegie Mellon University
Cross Validation
Question
You have 100 medical patients to train a will survive surgery
classifier
You