CS 534 - Machine Learning
Spring 2011

Overview

This course provides a broad introduction to machine learning and data mining. Topics include: supervised learning (discriminative/generative learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction); learning theory (bias/variance tradeoffs; VC theory; large margins); ensemble learning (bagging, boosting). If time allows, we will also cover sequential learning problems and algorithms. Lectures will discuss general issues in these topics and well-established algorithms, both from a computational aspect (how to compute the answer) and a statistical aspect (how to ensure that future predictions are accurate).

Learning Objectives of the Course:

1. Be able to formulate machine learning problems corresponding to different applications. 

2. Understand a range of machine learning algorithms along with their strengths and weaknesses. 

3. Understand the basic theory underlying machine learning. 

4. Be able to aply machine learning algorithms to solve problems of moderate complexity.

5. Be able to read current research papers and understand the issues raised by current research.

Exams

There will be two exams:
Exam I: 5/4/11
Final exam: 6/7/11

Assignments

The assignments in this course will consist of written problem sets and experimental assignments. The written homework problems are designed to help students build analytical skills required to carry out research related to machine learning. Note that the written assignment will not be graded based on correctness. Rather the instructor will record the number of problems that were "completed" (either correctly or incorrectly). Completing a problems requires demonstrating a non-trivial attempt at solving the problem. The judgment of whether a problem was "completed" is left to the instructor.

Grades

The final grade will be calculated based on the following breakdown: midterm 25%, final 25%, final project 25%, implementation assignments 25%. In addition, the resulting letter grade will be decreased by one if a student fails to complete at least 90% of the written homework problems.

Honor Code

Collaboration on assignments is permitted; copying of solutions or code is not. The work you hand in should be your own. Students should indicate on their homework, the names of all collaborators. While some students find studying together to be quite beneficial and enjoyable, I strongly encourage you to attempt to solve homework problems on your own first, as this is the only way to ensure that you have mastered the material. Generating solutions is much different than verifying solutions.

Back