CSE 493G1/599G1: Deep Learning

Class: T/Th 10:00-11:20am (CSE2 G20)

Recitation: Fri 9:30-10:20am (MGH 241), Fri 12:30-1:20pm (ECE 125)

Links:

Gradescope (Entry Code: R5KJXK), Ed Board, Canvas, Exam Archive, Project Archive



Teaser of Deep Learning

Course Description

This course is a deep dive into the details of deep learning algorithms, architectures, and tasks, with a focus on end-to-end models. We begin by grounding deep learning advancements particularly for the task of image classification; later, we generalize these ideas to many other tasks. During the 10-week course, students learn to implement and train their own neural networks and gain a detailed understanding of cutting-edge research in deep learning. Additionally, the final assignment provides the opportunity to train and apply multi-million parameter networks on student-chosen real-world vision problems. Through multiple hands-on assignments and the final course project, students acquire the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks.

Course Staff + Office Hours

Instructor
Head TA
Teaching Assistants
Ranjay Krishna
Tanush Yadav
Xiaojuan Wang
Lindsey Li
Scott Geng
Haoquan Fang
Vishnu Iyengar
Weikai Huang
Ranjay Krishna
Tanush Yadav
Xiaojuan Wang
Lindsey Li
Scott Geng
Haoquan Fang
Vishnu Iyengar
Weikai Huang
Hours: Tuesday,
Hours: TBD,
Hours: TBD,
Hours: TBD,
Hours: Monday,
Hours: Friday,
Hours: TBD,
Hours: Thursday,
12:00 PM - 1:00 PM
TBD
TBD
TBD
9:00 AM - 10:30 AM
2:30 PM - 4:00 PM
TBD
5:00 PM - 6:30 PM
CSE2 304
TBD
TBD
TBD
TBD
TBD
TBD
TBD
ranjay@cs
.washington.edu
tanush@cs
.washington.edu
xiaojwan@cs
.washington.edu
linjli@cs
.washington.edu
sgeng@cs
.washington.edu
hqfang@cs
.washington.edu
vishnuiy@cs
.washington.edu
weikaih@cs
.washington.edu

Prerequisites

Calculus (Math 126), Linear Algebra (Math 208), and Probability (CSE 312 or Math 394). While it is recommended to have some prior background in Machine Learning, the necessary fundamentals will be covered as part of this class.


Course Format

This class consists of lectures & recitations, 5 assignments, 1 in-class exam, and a course project.