(Spring 2023) CS747: Deep Learning

Instructor: Mingrui Liu

Description

Time/Location

• Tuesday 4:30pm—7:10pm, David King Jr. Hall Room 1006

Office Hours:

• Monday 2pm—3pm or by appointment

Contact Information:

• Office: Research Hall 355

• Email: (firstname)l (at) gmu (dot) edu

Recommended Textbooks:

• Goodfellow, Bengio, Courville. Deep Learning

Tentative Schedule

• Jan 24 (week 1): Introduction, Course Overview, Machine Learning Basics

• Jan 31 (week 2): Linear Classifier, Multi-class Classification

• Feb 7 (week 3): Neural Networks, backpropagation, automatic differentiation

• Feb 14 (week 4): Convolutional Neural Networks

• Feb 21 (week 5): Neural Network Training, Optimization, Generalization

• Feb 28 (week 6): Generative Adversarial Networks

• Mar 7 (week 7): Adversarial Examples: Attack and Defense

• Mar 14: Spring Break (No Class)

• Mar 21 (week 8): Recurrent Neural Networks

• Mar 28 (week 9): Transformers

• Apr 4 (week 10): Deep Reinforcement Learning

• Apr 11 (week 11): Convex Optimization, Convergence Rates, Nonconvex Optimization

• Apr 18 (week 12): Distributed Deep Learning, Federated Learning

• Apr 25 (week 13): Final Project Presentation

• May 2 (week 14): Final Project Presentation

Grading Policy

Grades:

• A: greater than 93

• A-: [90, 93)

• B+: [87, 90)

• B: [83, 87)

• B-: [80, 83)

• C+: [77, 80)

• C: [73, 77)

• C-: [68, 73)

• D: [60, 68)

• Fail: below 60

Weights:

• Homework: 50% (5 assignments in total)

• Project proposal/presentation: 15%

• Project Report: 30%

• Class Participation: 5%

Late penalty:

• Late submissions for whatever reason will be punished. 5% of the score of an assignment/project will be deducted per day with maximum tolerance 3 days. For example, if an assignment is submitted 2 days and 1 minute later than the deadline (counted as 3 days) and it gets a grade of 90%, then the score after the deduction will be: 95% - 3*5% = 80%.

Honor Code