Machine Learning (EECS 349)

Fall Quarter 2007

Electrical Engineering and Computer Science

Northwestern University

Basics

Policies

Calendar

Helpful Links

COMPLETED FINAL PROJECTS

Course Basics (to top)

Machine Learning is the study of algorithms that improve automatically through experience. Topics covered typically include Bayesian learning, decision trees, genetic algorithms, Markov models and neural networks. The course goals include:

To expose students to concepts and methods in machine learning.

To give students a basic set of machine learning tools applicable to a variety of problems.

To teach students critical analysis of machine learning approaches so that the student can determine when a particular technique is applicable to a given problem.

prerequisites: Significant prior programming experience (Equivalent to CS 211), graduate standing, or instructor permission

location of classroom: Annenberg G29

days and hours class meets: Mon, Wed, Fri 1:00pm – 1:50pm

final exam: Thursday, Dec 13, 9:00am – 10:50am

textbook(s): Machine Learning, Tom Mitchell, McGraw Hill, 1997

supplementary reading: Selected papers, assigned in class

Instructor

name: Bryan Pardo

office location: 3-323 Ford Building

office phone number: 847 491 7184

email: go to www.northwestern.edu and search for “Bryan Pardo”

office hours:

2:00pm – 2:50 pm, Wednesday

Course Policies (to top)

Grading

Homework assignments make up 50% of the grade and are a mix of laboratory assignments, reading assignments and problem sets. There is a group project worth 30% of the final grade. There is a midterm examination worth 20% of the grade.

Grading is straightforward. The total points for all projects sum to 100. Those receiving 93-100 points receive an A. Those with 90-92 receive an A minus, and so on. All students will have the chance to earn 5 points of extra credit. This is equivalent to a ½ letter grade boost. No other alterations to grades will be made. There is no curve.

Category	Points
Homework	70%
Final Project	30%
Extra-credit	5%
Total possible	105%

Submitting Work

Each homework assignment must be handed in as specified in the particular homework assignment. We are not responsible for homework left in mailboxes. Programming assignments must be submitted electronically, as specified in the lab assignment.

*NOTE* Assignments are due at the start of class on the day specified. Late assignments will not be graded. Thus, it is better to hand in a partial assignment on time than to receive zero credit for a complete assignment handed in late.

Attendance and Lateness

Attendance is not taken. Lateness is a disruption to the class. Do your level best not to be late. Late assignments will not be graded.

Academic Dishonesty

Do your own work. Academic dishonesty will be dealt with as laid out in the student handbook.

Course Calendar/Schedule (Subject to change) (to top)

Week	Day	Date	Topic	Reading	Assigned	Due	Points
1	Wed	26-Sep-07	NO CLASS
1	Fri	28-Sep-07	Intro to the Class
2	Mon	1-Oct-07	Some basics	Chapter 2
2	Wed	3-Oct-07	Classification with Decision Trees	Chapter 3	HW 1
2	Fri	5-Oct-07	Decision Trees
3	Mon	8-Oct-07	Measuring error & Hill Climbing
3	Wed	10-Oct-07	Graphical Models: Perceptrons	Chapter 4
3	Fri	12-Oct-07	Graphical Models: Multi-Layer Perceptrons			HW 1	10
4	Mon	15-Oc-07	Genetic Algorithms	Chapter 9	HW 2
4	Wed	17-Oct-07	Designing your final project	Genetic Algorithms	Final project proposal
4	Fri	19-Oct-07	Genetic Programming
5	Mon	22-Oct-07	Statistics: Sample error, confidence	Chapter 5
5	Wed	24-Oct-07	Statistics: Central limit theorem, etc
5	Fri	26-Oct-07	MLE, MAP, Issues with these	Chapter 6		Final project proposal	5
6	Mon	29-Oct-07	Bayesian Reasoning	* To be determined *
6	Wed	31-Oct-07	Bayesian Reasoning	Sentiment Classification		HW 2	15
6	Fri	2-Nov-07	Bayesian Reasoning
7	Mon	5-Nov-07	Markov Models	HMM Tutorial	HW 3
7	Wed	7-Nov-07	Markov Models	Score following
7	Fri	9-Nov-07	Markov Models
8	Mon	12-Nov-07	Reinforcement learning	Chapter 13
8	Wed	14-Nov-07	Reinforcement learning	TD Gammon paper		HW 3	15
8	Fri	16-Nov-07	Reinforcement learning
9	Mon	19-Nov-07	Group project status reports	Chapter 7	HW 4	Group project status reports	5
9	Wed	21-Nov-07	Computational Learning Theory
9	Fri	23-Nov-07	THANKSGIVING	THANKSGIVING	THANKSGIVING	THANKSGIVING
10	Mon	26-Nov-07	Boosting	Intro to Boosting
10	Wed	28-Nov-07	Boosting			HW 4	15
10	Fri	30-Nov-07	Group project status reports			Group project status reports	5
11	Mon	3-Dec-07	Support Vector Machines (briefly)	* To be determined *	HW 5
11	Wed	5-Dec-07	Clustering
11	Fri	7-Dec-07	Clustering			HW 5	15
Finals Week	Thu	12:01 AM 13-Dec-07	Final Project Website Final Project Paper			DUE AT 12:01 AM Final Project Website Final Project Paper	5 10

Helpful Links (to top)

Datasets

The Yale Face dataset - The database contains 5760 single light source images of 10 subjects each seen under 576 viewing conditions (9 poses x 64 illumination conditions).

The UCI Machine Learning dataset repository – Many useful datasets in text format

The University of Iowa Instrument Recording repository – If you want to learn the difference between different musical instrument sounds, this is a useful set.

The Statlab collection of datasets – Has things like A pre-classified dataset containing 11,000 web pages from 11 different categories and data on salaries of Major League Baseball players.

Datasets used in the book Pattern Recognition and Machine Learning