Instructor: Mingrui Liu
Time/Location
Office Hours:
Contact Information:
Office: ENGR 5322
Email: (firstname)l (at) gmu (dot) edu
This course presents the theory, underlying principles and applications of Deep Learning (DL). Deep learning is a Machine Learning approach based on learning data representations as opposed to designing task-specific algorithms. The course covers the concepts of Multilayer Perceptrons (MLPs) and algorithms to train them (gradient descent, backpropagation), Regularization of DL, Convolutional Networks (CNNs), Autoencoders, Recurrent Networks (RNNs), and Deep Generative Models including Generative Adversarial Methods. Problems from various application domains such as natural language processing and computer vision will be discussed.
Recommended Textbooks:
Goodfellow, Bengio, Courville. Deep Learning
Aug 26 (week 1): Introduction, Course Overview, Machine Learning Basics
Sep 2 (week 2): Linear Classifier, Multi-class Classification
Sep 9 (week 3): Neural Networks, Backpropagation, Automatic Differentiation
Sep 16 (week 4): Convolutional Neural Networks
Sep 23 (week 5): Neural Network Training, Optimization, Generalization
Sep 30 (week 6): Generative Adversarial Networks
Oct 7 (week 7): Adversarial Examples: Attack and Defense
Oct 14 (week 8): Recurrent Neural Networks
Oct 21 (week 9): Transformers
Oct 28 (week 10): Transformers, Deep Reinforcement Learning
Nov 4 (week 11): Deep Reinforcement Learning
Nov 11 (week 12): Reinforcement Learning with Human Feedback, Reasoning
Nov 18 (week 13): Final Project Presentation
Nov 25: Thanksgiving Recess, No Class
Dec 2 (week 14): Final Project Presentation
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.
Please see the Office for Academic Integrity (https://oai.gmu.edu/) for a full description of the code and the honor committee process, and the Honor Code Policies of the Department of Computer Science (https://cs.gmu.edu/resources/honor-code/) regarding the course project. GMU is an Honor Code university. The principle of academic integrity is taken seriously and violations are treated gravely. If you rely on someone else's work in an aspect of the course project, you should give full credit in the proper, accepted form. Another aspect of academic integrity is the free play of ideas. Vigorous discussion and debate are encouraged in this course, with the firm expectation that all aspects of the class will be conducted with civility and respect for differing ideas, perspectives, and traditions. When in doubt (of any kind) please ask for guidance and clarification.