Meeting Times: Mondays and Wednesdays, 2:00-3:15
Location: College of Computing CCB 103

Instructor: Edmond Chow
E-mail:
Office hours: TBD

TA: Conlain Kelly
E-mail: ckelly84@gatech.edu
Office hours: TBD


Course Description

This course is designed for students who want to better understand machine learning methods through looking at pseudocode and programming them. We will implement machine learning algorithms and experiment with how they work on different types of data. The course is open to all majors at Georgia Tech.

In addition, this course will provide and strengthen the mathematical background needed to develop intuition for deeply understanding machine learning algorithms. Statistics, numerical optimization, and linear algebra will be used at a fundamental level necessary for quickly grasping and extending the main ideas behind machine learning.

This course is intended to be more abstract than other courses in machine learning, and applications of machine learning will not be discussed. This course is especially suited to students who wish to pursue further courses or self-study in machine learning.

Prerequisites

Programming in any language (examples will be given in Matlab). You should also be comfortable with multivariable calculus (MATH 2551/2552), linear algebra (MATH 1554), and concepts in probability and statistics.

Some Topics

  • Statistics background
  • Regularization
  • Bayesian regression and classification
  • Gaussian processes
  • Support vector machines
  • Kernel methods in general
  • Neural networks
  • Constrained optimization and stochastic optimization

Grading

100% Assignments
There will be a short assignment about every 1.5 weeks. Many assignments will build on previous assignments. Note that the final assignment will be due during final exam week.

References

There is no required textbook. Below are some texts that would be useful for this course. Several are freely available online.