Course Description

This course will cover fundamental concepts in pattern recognition and machine learning. We will focus on mathematical formulations and computational methods that are broadly applicable. Topics include supervised learning, parametric and non-parametric models, decision theory, bayesian inference, dimensionality reduction, clustering, feature selection, generalization bounds, support vector machines and neural networks. We will consider motivating applications in computer vision, signal processing, medical diagnostics, and information retrieval.

Prerequisites: probability and statistics, linear algebra, calculus and programming experience.

Textbook: C. Bishop, Pattern Recognition and Machine Learning, Springer.

Grading: Grading will be based on regular homework assignments and a final exam. Homework will involve both mathematical exercises and programming assignments/projects. Students can use python or Matlab for programming.