Computer Science 682 - Neural Networks: Modern Intro

This course will focus on modern, practical methods for deep learning with neural networks. The course will begin with a description of simple classifiers such as perceptrons and logistic regression classifiers, and move on to standard neural networks, convolutional neural networks, some elements of recurrent neural networks, and transformers. The emphasis will be on understanding the basics and on practical application more than on theory. Many applications will be in computer vision, but we will make an effort to cover some natural language processing (NLP) applications as well. The current plan is to use Python and associated packages such as Numpy and TensorFlow. Required background includes Linear Algebra, Probability and Statistics, and Multivariate Calculus. All assignments will be in the Python programming language.

Open to Graduate students only. REQUIRED BACKGROUND FOR THE COURSE INCLUDES THE FOLLOWING. MULTIVARIATE CALCULUS, LINEAR ALGEBRA, AND PROBABILITY AND STATISTICS. PROGRAMMING IN PYTHON OR EQUIVALENT HIGH LEVEL LANGUAGE. SEATS HELD FOR INCOMING GRAD STUDENT REGISTRATION. UNDERGRADUATES AND STUDENTS NEEDING SPECIAL PERMISSION MUST REQUEST OVERRIDES VIA THE ON-LINE FORM: https://www.cics.umass.edu/overrides.