Machine Learning

 

CSCI 5622 Section 001

 

Location:

Tuesday and Thursday 9:30-10:45 ECCR 1B08

Instructor:

Professor Greg Grudic

Office:

ECOT 525

Office Hours:

Tuesday and Thursday 11:00-12:30

Phone:

303-492-4419

Email:

grudic@cs.colorado.edu

Course URL:

http://www.cs.colorado.edu/~grudic/teaching/CSCI5622

 

 

Grading:

Homework 50%

Project 25%

Class Participation 5%

Final 20%

 

 

Textbook: Machine Learning by Tom Mitchell.

 

 

Goals: Understand the theory and practice of the most commonly used Machine Learning Algorithms. After taking the course you will be able to 1) read current research papers in machine learning and 2) understand the relevant issues addressed by these papers. In other words, you should be able to do basic (relevant) research in machine learning after taking this course.

 

 

 

Lecture Schedule

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Aug 28 Introduction

Aug 30 Nearest neighbor [Chapter 8.1-8.3]

 

Sep 04 Probabilistic networks: Naive Bayes [Section 6.9-6.11]

Sep 06 Hypothesis Evaluation [Chapter 5} - HW1 assigned

 

Sep 11 Decision Trees C4.5 [Chapter 3.1-3.6, 3.7.2]

Sep 13 Decision Trees (Finish)

 

Sep 18 PAC Learning [Chapter 7.1-7.3]

Sep 20 PAC Learning with continuous parameters [Chapter 7.4] - HW1 due, HW2 assigned

 

Sep 25 Simple Neural Networks I [Chapter 4.1-4.4]

Sep 27 Simple Neural Networks II

 

Oct 02 Multilayer Neural Networks [Chapter 4.5-4.7]

Oct 04 FALL BREAK

 

Oct 09 Neural Networks tricks and variations [Chapter 4.8] - HW2 due, HW3 assigned

Oct 11 Neural Networks tricks and variations [Chapter 6.5; 8.4; 12.3-12.4]

 

Oct 16 Bayesian Learning Theory [Chapter 6.1-6.8]

Oct 18 Rate of Convergence and Computational Complexity properties.

 

Oct 23 Support Vector Machines

Oct 25 Support Vector Machines

 

Oct 30 Bias Variance Theory (Bagging) - HW3 due, HW4 assigned

Nov 01 Bias Variance Theory (Boosting) Selection of Final Project

 

Nov 06 Unsupervised Learning I - HW4 due

Nov 08 Unsupervised Learning II

 

Nov 13 Reinforcement Learning I Ch 13

Nov 15 Reinforcement Learning II

 

Nov 20 Genetic Algorithms

Nov 22 THANKSGIVING

 

Nov 27 Review I

Nov 29 Review II

 

Dec 04 NIPS

Dec 06 NIPS

 

Dec 11 Presentation of Final Projects

Dec 13 Presentation of Final Projects