Overview

Description

CALENDAR DESCRIPTION:

Machine learning has become the main framework for building programs that perform intelligent tasks. In fields such as computer vision and natural language processing, many recent successes have been achieved using neural nets with several layers, so-called deep neural nets. Students will look at deep neural nets, techniques for training them from data, and significant applications. They will be presented with network architectures such as convolutional neural nets, autoencoders, recurrent neural nets, long-short term memory networks, and generative adversarial networks. Advanced training techniques to be described include dropout, batch normalization, and adaptive step size selection.

COURSE DETAILS:

Machine learning has become the main framework for building programs that perform intelligent tasks. In fields such as computer vision and natural language processing, many recent successes have been achieved using neural nets with several layers, known as deep neural nets. This course is an introduction to deep neural nets, techniques for training them from data, and significant applications. The main learning outcomes are 1) sufficient practical experience with deep learning to apply current techniques to real-life problems 2) sufficient theoretical understanding of deep neural nets to analyze and improve their performance.

Course Requirement Notes: You will find it difficult to succeed without a background in machine learning and the requisite mathematics (calculus, linear algebra, probability). There will be a background quiz to give you feedback on whether you are prepared.

Grading

Materials

MATERIALS + SUPPLIES:

Reference Books

• Deep Learning, Goodfellow, Bengio, and Courville, MIT Press, 2016, 9780262035613, Available on-line at http://www.deeplearningbook.org
• Introduction to Deep Learning, Eugene Charniak, MIT Press, 2018, 9780262039512

REQUIRED READING NOTES: