Machine Learning, 10-701 and 15-781

Prof. Carlos Guestrin
School of Computer Science, Carnegie Mellon University

Spring 2006

Class lectures: Mondays & Wednesdays from 10:30-11:50 in Wean Hall 7500

Review sessions: Thursdays 5:00-6:30 in Wean Hall 5409

It is hard to imagine anything more fascinating than automated systems that improve their own performance. The study of learning from data is commercially and scientifically important. This course is designed to give a graduate-level student a thorough grounding in the methodologies, technologies, mathematics and algorithms currently needed by people who do research in learning and data mining or who may need to apply learning or data mining techniques to a target problem. The topics of the course draw from classical statistics, from machine learning, from data mining, from Bayesian statistics and from statistical algorithmics.

Students entering the class should have a pre-existing working knowledge of probability, statistics and algorithms, though the class has been designed to allow students with a strong numerate background to catch up and fully participate.

Instructor

Carlos Guestrin, Wean Hall 5313, x8-3075, guestrin@cs, Office hours: Tuesdays 1:30-2:30pm

Teaching Assistants

Anton Chechetka , NSH 1602A, x8-8780, antonc@cs, Office hours: Tuesdays 4:45-6:45
Stanislav Funiak , NSH 4222, x8-3132, sfuniak@cs, Office hours: Fridays 1:15-3:15
Andreas Krause Wean 3701, x8-1723, krausea@cs, Office hours: Wednesdays 4:00-6:00
Jure Leskovec , Wean 5123, x8-5728, jure@cs, Office hours: Mondays 1:00-3:00

Questions

The first point of contact for questions pertaining to homework problems is according to the following schedule. Please contact the TA specific to the homework problem that you have a question about. Also, questions may be emailed to 10701-instructors@cs.cmu.edu.

HMWK #1 Out: 23-Jan In: 8-Feb (new date!!!) Assignment: [PDF] Solutions: [PDF]	Prob. #1: Stano
	Prob. #2: Jure Chess dataset [zip]
	Prob. #3: Andreas
	Prob. #4: Anton

HMWK #2 Out: Feb 9 In: Feb 20 Updated assignment with more hints: [PDF] Solutions: [PDF] Consistency checker for Q1.2: [code] Voting dataset [zip]	Prob. #1: Anton Prob. #2,3: Stano

HMWK #3
Out: 20-Feb
In: 1-Mar
Assignment: [PDF]
Solutions: [PDF]
libsvm download [link]
Matlab and data files [zip]

Andreas, Jure

MIDTERM
Solutions [PDF]

HMWK #4
Out: 22-Mar
In: 5-Apr
Assignment: [PDF]
Solutions: [PDF]
Matlab and data files [zip]

HMWK #5
Out: 5-Apr
In: 19-Apr
Assignment: [PDF]
Matlab and data files [zip]
Solutions: [PDF]

Course Assistant

Terrill L. Frantz, TerrillFrantz@cmu, Smith Hall 231

Adminstrative Assistant

Monica Hopes, x8-5527, meh@cs, Wean Hall 4616

Textbooks

Optional textbook: Machine Learning, Tom Mitchell.
Optional textbook: Pattern Classification (2nd Edition), Duda, Hart and Stork.
Optional textbook: Neural Networks for Pattern Recognition, Chris Bishop.

Announcement Emails

Class announcements will be braodcast using a group email list: 10701-announce@cs.cmu.edu
If you are registered for the course, you have automatically been added to the mail group. If you are for some reason NOT receiving these announcements, you can subscribe via the 10701-announce list page.
For changes (incl. additions or removal) to your membership in the course list, please make changes directly via the list administration page [https://mailman.srv.cs.cmu.edu/mailman/listinfo/10701-announce]

Course Website (this page)

http://www.cs.cmu.edu/~guestrin/Class/10701
Corrections or comments to Terrill Frantz (TerrillFrantz@cmu).

Grading

Final grades will be based on midterm (20%), homework (5 assignments, 30%), final project (20%), and final exam (30%).

Collaboration policy

Homeworks will be done individually: each student must hand in their own answers. It is acceptable, however, for students to collaborate in figuring out answers and helping each other solve the problems. We will be assuming that, as participants in a graduate course, you will be taking the responsibility to make sure you personally understand the solution to any work arising from such collaboration. You also must indicate on each homework with whom you collaborated. The final project may be completed by small teams.

Late homework policy

You will be allowed 3 total late days without penalty for the entire semester. For instance, you may be late by 1 day on three different homeworks or late by 3 days on one homework. Once those days are used, you will be penalized according to the policy below:
- Homework is worth full credit at the beginning of class on the due date.
- It is worth half credit for the next 48 hours.
- It is worth zero credit after that.
You must turn in all of the 5 homeworks, even if for zero credit, in order to pass the course.
Turn in all late homework assignments to Monica.

Homework regrades policy

If you feel that we have made an error in grading your homework, please turn in your homework with a written explanation to Sharon, and we will consider your request. Please note that regrading of a homework may cause your grade to go up or down.

Final project

Project details are out!

Out March 1st

Project proposal due Wednesday, March 22th

Graded milestone due Wednesday, April 12th (20% of project grade)

Poster session Friday, May 5th 2:00-5:00pm; NSH Atrium

Paper due May 8th

For project milestone, roughly half of the project work should be completed. A short, graded write-up will be required, and we will provide feedback.

Lecture schedule

Module

Material covered

Class details, online material, and homework

Module 1; Basics
(1 Lectures)

What is learning?
- Version spaces
- Sample complexity
- Training set/test set split
Point estimation
- Loss functions
- MLE
- Bayesian
- MAP
- Bias-Variance trade off

Mon., Jan 16:
	No Class. MLK B-Day

Wed., Jan 18:
	Lecture: What's ML, Point estimation [Slides] [Annotated] Reading: Koller & Friedman, Chapter 1 (1.1-1.2, but the whole chapter is useful). To be distributed in the Jan. 19 recitation, and Jan. 23 class. Additional Reference: Andrew Moore's basic probability tutorial

Module 2: Linear models
(3 Lectures)

Linear regression [Applet]
http://www.mste.uiuc.edu/users/exner/java.f/leastsquares/
Bias-Variance tradeoff
Overfitting
Bayes optimal classifier
Naive Bayes
Logistic regression
Discriminative v. Generative models

Mon., Jan. 23: Lecture: Gaussians, Linear Regression, Bias-Variance Tradeoff [Slides] [Annotated]
		Homework #1 out Assignment: [PDF] Prob#2 Chess dataset [zip]

Wed., Jan 25:
	Lecture: Overfitting, What's learning - revisited, Naive Bayes [Slides] [Annotated]

Mon., Jan 30:
	Lecture: Naive Bayes, Generative v. Discriminative, Logistic Regression [Slides] [Annotated] Required Reading: Mitchell's Chapter on Naive Bayes and Logistic Regression Optional Reading: Ng and Jordan's NIPS 2001 paper on Discriminative versus Generative Learning

Module 3: Non-linear models
Model selection
(5 Lectures)

Decision trees
Overfitting, again
Regularization
MDL
Cross-validation
Boosting [Adaboost Applet]
www.cse.ucsd.edu/~yfreund/adaboost
Instance-based learning [Applet]
www.site.uottawa.ca/~gcaron/applets.htm
- K-nearest neighbors
- Kernels
Neural nets [CMU Course]
www.cs.cmu.edu/afs/cs/academic/class/15782-s04/

Wed., Feb. 1:
	Lecture: Logistic Regression, Decision Trees [Slides] [Annotated]

Mon., Feb 6:
	Lecture: Decision Trees, Boosting [Slides] [Annotated] Reading: Schapire Boosting tutorial

Wed., Feb. 8:
	Lecture: Boosting, Cross Validation, Simple Model Selection, Regularization, MDL [Slides] [Annotated]		EXTENSION: Homework #1 due (beginning of class) Homework #2 out Updated assignment with more hints: [PDF] Voting dataset [zip]

Mon., Feb. 13:
	Lecture: Cross Validation, Simple Model Selection, Regularization, MDL, Neural Nets [Slides] [Annotated]

Wed., Feb. 15:
	Lecture: Neural Nets, Instance-based Learning [Slides] [Annotated]

Module 4: Margin-based approaches
(2 Lectures)

SVMs [Applets]
www.site.uottawa.ca/~gcaron/applets.htm
Kernel trick

Mon., Feb 20:
	Lecture: Instance-based Learning, SVMs [Slides] [Annotated]	Homework #2 due (beginning of class) Homework #3 out

Wed., Feb. 22:
	Lecture: SVMs [Slides] [Annotated] Reading: Hearst 1998: High Level Presentation Reading: Burges 1998: Detailed Tutorial

Module 5: Learning theory
(3 Lectures)

Sample complexity
PAC learning [Applets]
www.site.uottawa.ca/~gcaron/applets.htm
Error bounds
VC-dimension
Margin-based bounds
Large-deviation bounds
- Hoeffding's inequality, Chernoff bound
Mistake bounds
No Free Lunch theorem

Mon., Feb. 27:
	Lecture: SVMs - The Kernel Trick [Slides] [Annotated]

Wed., Mar. 1
	Lecture: SVMs - The Kernel Trick, Learning Theory [Slides] [Annotated]	Homework #3 due (beginning of class) Project Out

Mon., Mar. 6
	Lecture: Learning Theory, Midterm review [Slides] [Annotated]

Mid-term Exam

All material thus far

Wed., Mar 8:
	Mid-term exam (in class)

Spring break

Mon., Mar. 13:
	No class

Wed., Mar. 15:
	No class

Module 6: Structured models
(4 Lectures)

HMMs
- Forwards-Backwards
- Viterbi
- Supervised learning
Graphical Models
- Representation
- Inference
- Learning
- BIC

Mon., Mar. 20:
	Lecture: Bayes nets - Representation [Slides] [Annotated]

Wed., Mar. 22:
	Lecture: Bayes nets - Representation (cont.), Inference [Slides] [Annotated]	Homework #4 out Project Proposal due (beginning of class)

Mon., Mar. 27:
	Lecture: Bayes nets - Inference (cont.), HMMs [Slides] [Annotated] Reading: Rabiner's Detailed HMMs Tutorial

Wed., Mar. 29:
	Lecture: HMMs Bayes nets - Structure Learning [Slides] [Annotated] Additional Reading: Heckerman BN Learning Tutorial Additional Reading: Tree-Augmented Naive Bayes paper

Module 7: Unsupervised
and semi-supervised learning
(4 Lectures)

K-means

Applet: K-means

Expectation Maximization (EM)

mixture of Gaussians

Applet: Mixture of Gaussians

for training Bayes nets
for training HMMs

Combining labeled and unlabeled data

EM
reweighting labeled data
Co-training
unlabeled data and model selection

Dimensionality reduction

PCA, SVD

Applet: PCA

Feature selection

Mon., Apr. 3:
	Lecture: Bayes nets - Structure Learning Clustering - K-means & Gaussian mixture models [Slides] [Annotated]

Wed., Apr. 5:
	Lecture: Clustering - K-means & Gaussian mixture models [Slides] [Annotated] Reading: Neal and Hinton EM paper	Homework #4 due (beginning of class) Homework #5 out

Mon., Apr. 10:
	Lecture: EM Baum-Welch (EM for HMMs) [Slides] [Annotated]

Wed., Apr. 12:
	Lecture: Baum-Welch (EM for HMMs) EM for Bayes Nets [Slides] [Annotated] Reading: Ghahramani, "An introduction to HMMs and Bayesian Networks"	Project milestone due (beginning of class)

Module 8: Learning to make decisions
(3 Lectures)

Markov decision processes
Reinforcement learning

Mon., Apr. 17:
	Lecture: EM for Bayes Nets Co-Training for semi-supervised learning [Slides] [Annotated] Reading: Blum and Mitchell co-training paper Optional reading: Joachims Transductive SVMs paper

Wed., Apr. 19:
	Learning from text data Lecture by Tom Mitchell	Homework #5 due (beginning of class)

Mon., Apr. 24:
	Lecture: Semi-supervised learning in SVMs Principal Component Analysis (PCA) [Slides] [Annotated] Reading: Shlens' PCA tutorial Optional reading: Wall et al. 2003 - PCA for gene expression data

Module 9: Advanced topics
(3 Lectures)

Text data
Hierarchial Bayesian models
Tackling very large datasets
Active learning
Overview of follow-up classes

Wed., Apr. 26:
	Lecture: Principal Component Analysis (PCA) (cont.) Markov Decision Processes [Slides] [Annotated] Reading: Kaelbling et al. Reinforcement Learning tutorial

Mon., May 1:
	Lecture: Markov Decision Processes Reinforcement Learning [Slides] [Annotated] Reading: Brafman and Tennenholtz: Rmax paper

Wed., May 3:
	Lecture: Reinforcement Learning Big Picture [Slides] [Annotated]

Project Poster Session

Fri., May 5: Newell-Simon Hall Atrium 2:00-5:00pm

Project Paper

Mon., May 8: Project paper due

Final Exam

All material thus far

Friday, May 12th, 1-4 p.m. Location TBD

Recitation

All recitations are Thursdays, 5:00-6:30, Wean Hall 5409, unless otherwise noted.

Date	Instructor	Topic
Jan. 19	Stano	Review of Probability; Distributions; Bayes Rule
Jan. 25 Wed. 5:00-7:00pm NSH 3305	Jure	Introduction to Matlab [FILES Directory]
Jan. 26	Anton	Linear regression, overfitting, examples. [Slides] [Matlab code]
Feb. 2	Andreas
Feb. 9	Jure	Information Gain, Decision Trees and Boosting. [Slides]
Feb. 16	Stano	Cross-validation, Neural networks.
Feb. 23	Anton	Nearest neighbors, weighted linear regression, SVMs
Mar. 2	Andreas
Mar. 6 5-7pm	All	Midterm review session, MONDAY 6th, in NSH 3305. Please bring questions.
Mar. 9		**NO RECITATION
Mar. 16*		**NO RECITATION -- SPRING BREAK
Mar. 23	Jure	Review of the midterm exam.
Mar. 30	Stano	Bayesian networks. [Slides]
Apr. 6	Anton	Gaussians, Gaussian Mixtures, EM
Apr. 13	Andreas	EM for Hidden Markov Models
Apr. 20*		** NO RECITATION -- University Closed
Apr. 27	Jure	Dimensionality reduction: PCA, SVD, Graphs, PageRank, Power iteration [Slides]
May 4
May 8	Andreas	MDPs and Reinforcement Learning, Monday 8, 5 pm in NSH 3305.
May 10	Stano	Final exam review session, Wednesday 10, 5:30 pm in NSH 1305.

Exam Schedule

Note: both the midterm and the final will be open book, notes, papers, etc., but you are not allowed to use a computer.

Midterm: Wednesday, Mar. 8, 10:30-11:50 am, Wean Hall 7500 (in class).

Final: Friday, May 12th, 1-4 p.m., location TBA

Additional Resources

Here are some example questions here for studying for the midterm/final. Note that these are exams from earlier years, and contain some topics that will not appear in this year's final. And some topics will appear this year that do not appear in the following examples.

DTREE slides with annotations from review session on Monday

The 2001 midterm exam

The 2001 midterm solutions

The 2001 final exam

Solutions to the 2001 final exam

The 2002 midterm exam

Solutions to the 2002 midterm exam

Additional examples of midtermlike questions (PS) or (PDF)

Solutions to the additional examples (PS) or (PDF)

Final Exam 2002 (some figs missing)

Answers for final Exam 2002

Andrew's handwritten answers for final Exam 2002

The 2003 midterm exam

Handwritten annotations to 2003 midterm by Ajit on Thursday evening

Solutions to the 2003 midterm exam

Final Exam 2003

Answers for final Exam 2003

The 2004 midterm exam

Solutions to the 2004 midterm exam

Spring 2005 course webpage

Fall 2005 course webpage

Note to people outside CMU

Feel free to use the slides and materials available online here. Please email the instructors with any corrections or improvements. Additional slides and software are available at the Machine Learning textbook homepage and at Andrew Moore's tutorials page.