Skip to Main Content

DATAC182

Download as PDF

DATA C182 - Designing, Visualizing and Understanding Deep Neural Networks

Data Science Undergraduate Studies Undergraduate CDSS - Clg of Comp Data Sci & Society

Subject

DATA

Course Number

C182

Course Level

Undergraduate

Formerly Known As

Computer Science 182

Course Title

Designing, Visualizing and Understanding Deep Neural Networks

Course 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.

Minimum

4

Maximum

4

Grading Basis

Default Letter Grade; P/NP Option

Method of Assessment

Alternative Final Assessment

Instructors

Gonzalez

Prerequisites

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

Repeat Rules

Course is not repeatable for credit.

Credit Restriction Courses. Students will receive no credit for this course if following the course(s) have already been completed.

-

Credit Restrictions.

Students will receive no credit for COMPSCI 182 after completing COMPSCI W182, or COMPSCI L182.

Credit Replacement Courses. Upon passing, students can use the following course(s) to replace a deficient grade for this course.

-

Student Learning Outcomes

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

Cross-Listed Course(s)

Formats

Discussion, Lecture

Term

Fall and Spring

Duration (in weeks)

15

Minimum Hours

3

Maximum Hours

3

Lecture Mode of Instruction

In Person, Online

Minimum Hours

1

Maximum Hours

1

Discussion Mode of Instruction

In Person, Online

Minimum Hours

8

Maximum Hours

8