CS 182. Designing, Visualizing and Understanding Deep Neural Networks

Catalog Description: Deep Networks have revolutionized computer vision, language technology, robotics and control. They have growing impact in many other areas of science and engineering. They do not however, follow a closed or compact set of theoretical principles. In Yann Lecun's words they require "an interplay between intuitive insights, theoretical modeling, practical implementations, empirical studies, and scientific analyses." This course attempts to cover that ground.

Units: 4

Student Learning Outcomes: Students will learn design principles and best practices: design motifs that work well in particular domains, structure optimization and parameter optimization., Understanding deep networks. Methods with formal guarantees: generative and adversarial models, tensor factorization., Students will come to understand visualizing deep networks. Exploring the training and use of deep networks with visualization tools.

Prerequisites: MATH 53, MATH 54, and COMPSCI 61B; COMPSCI 70 or STAT 134; COMPSCI 189 is recommended.

Credit Restrictions: Students will receive no credit for COMPSCI 182 after completing COMPSCI W182, or COMPSCI L182. A deficient grade in COMPSCI 182 may be removed by taking COMPSCI W182, or COMPSCI L182.

Formats:
Spring: 3.0 hours of lecture and 1.0 hours of discussion per week
Fall: 3.0 hours of lecture and 1.0 hours of discussion per week

Grading basis: letter

Final exam status: Alternative method of final assessment


Class Schedule (Fall 2022):
TuTh 09:30-10:59, Soda 306 – Anant Sahai, PhD

Class Schedule (Spring 2023):
MoFr 09:00-10:29, Soda 306 – Anant Sahai, PhD

Spring 2019 class homepage on bCourses

Class homepage on inst.eecs

General Catalog listing