CSCE 636-600 Deep Learning
CSCE 636-600 Deep Learning
Instructor: Prof. Anxiao (Andrew) Jiang. Email: ajiang@cse.tamu.edu
Time and Location: 1/13/2025 to 5/6/2025, 3:55--5:10pm on Tuesdays and Thursdays, in 124 HRBB
TAs: Jeff Hykin (email: jeff.hykin+cs636@tamu.edu ) and Liudeng Wang (email: eureka@tamu.edu )
Office Hours:
Dr. Jiang's office hour: 11:00am--11:30am on Mondays, via Zoom at https://us04web.zoom.us/j/76827536251?pwd=m1GTxGUA7JrTSVwfkLP9fLTelI9dEM.1
(Meeting ID: 768 2753 6251, Passcode: 4qjnyu)
Liudeng Wang's office hours: 1:30-2:30pm on Tuesdays and 1:30-2:30pm on Wednesdays, via zoom at https://tamu.zoom.us/j/6557063576 (Meeting ID: 655 706 3576)
Jeff Hykin's office hours: 5:10 - 6:10pm on Thursdays and 4:00-5:00pm on Fridays, via zoom at https://tamu.zoom.us/j/9726131094
Grading and Requirements:
The final grade is based on homework and project. Homework: 25%. Three projects: 25% per project (75% total).
Submission Policy: An electronic copy of each homework should be submitted in https://canvas.tamu.edu. An electronic copy of each file for Projects should be emailed to moore.research.education@gmail.com. No late homework/project submission will be accepted. Students should double check each submission to make sure correct files are submitted. (If wrong files are submitted, correct files to replace them can only be submitted before the deadline, not after it.)
By default, all work is solo; no collaboration allowed unless stated otherwise.
Textbook:
Textbook: Deep Learning with Python, 2nd Edtion, by Francois Chollet.
Recommended Textbook: Deep Learning: Foundations and Concepts, 2024 edition, by Christopher M. Bishop and Hugh Bishop.
Thanks to the support of Texas A&M University Libraries, you can access the following course materials for free: Deep Learning with Python, https://go.oreilly.com/TAMU/library/view/-/9781617296864/?ar
Computing resources:
1. Google CoLab: an open and free Jupyter notebook environment by Google that runs in the cloud and allows us to use CPU, GPU and TPU resources. It requires no setup. It's a good resource for anyone who wants to do swift experiments in deep learning.
2. HPRC: You can apply for an account at TAMU HPRC (High Performance Research Computing). It has CPU and GPU resources.
1/14/2025 (Tuesday): Lecture 1: What is Deep Learning.
1/16/2025 (Thursday): Lecture 2: Mathematical Building Blocks of Neural Networks.
1/21/2025 (Tuesday): Class cancelled due to weather
1/23/2025 (Thursday): Lecture 2: Mathematical Building Blocks of Neural Networks.
1/28/2025 (Tuesday): Lecture 3: Getting Started with Neural Networks: Classification and Regression.
1/30/2025 (Thursday): Lecture 3: Getting Started with Neural Networks: Classification and Regression.
2/4/2025 (Tuesday): Lecture 4: Fundamentals of Machine Learning. Lecture 5: Working with Keras: A Deep Dive.
2/6/2025 (Thursday): Lecture 6: Introduction to Deep Learning for Computer Vision.
2/11/2025 (Tuesday): Self-study.
2/13/2025 (Thursday): Lecture 6: Introduction to Deep Learning for Computer Vision.
2/18/2025 (Tuesday): Lecture 7: Advanced Deep Learning for Computer Vision.
2/20/2025 (Thursday): Lecture 8: Deep Learning for Time Series.
2/25/2025 (Tuesday): Lecture 8: Deep Learning for Time Series. Lecture 9: Deep Learning for Text.
2/27/2025 (Thursday): Lecture 9: Deep Learning for Text.
3/4/2025 (Tuesday): Lecture 9: Deep Learning for Text.
3/6/2025 (Thursday): Lecture 9: Deep Learning for Text.
3/11/2025 (Tuesday): Spring break. No class.
3/13/2025 (Thursday): Spring break. No class.
3/18/2025 (Tuesday): Lecture 9: Deep Learning for Text. Discuss Project 1.
3/20/2025 (Thursday): Discuss Project 1. Supplementary Lectures on Linear Programming. (Lecture videos: Part 1 of 4)
3/25/2025 (Tuesday): Discuss Project 1. Supplementary Lectures on Linear Programming. (Lecture videos: Part 2 of 4, Part 3 of 4, Part 4 of 4)
3/27/2025 (Thursday): Lecture 10: Generative Deep Learning.
4/1/2025 (Tuesday): Lecture 10: Generative Deep Learning.
4/3/2025 (Thursday): Lecture 11: Best Practices for the Real World.
4/8/2025 (Tuesday): Q&A Session for Project 1, via zoom at 3:55--5:10pm. (The zoom link is the same as that for Prof. Jiang's office hour on Mondays, shown at the top of this webpage.) No in-class meeting.
4/10/2025 (Thursday): Lecture 12: Deep Reinforcement Learning (Slides and Lecture Video Part 1 of 3)
4/15/2025 (Tuesday): Lecture 12: Deep Reinforcement Learning (Slides and Lecture Video Part 1 of 3)
4/17/2025 (Thursday): Lecture 12: Deep Reinforcement Learning (Slides and Lecture Video Part 2 of 3)
4/22/2025 (Tuesday): Lecture 12: Deep Reinforcement Learning (Slides and Lecture Video Part 3 of 3)
4/24/2025 (Thursday): Lecture 13: Deep Reinforcement Learning: Q Learning (Slides and Lecture Video)
4/29/2025 (Tuesday): Redefined day(as Friday). No class.
Some Legacy Lecture Slides and Videos: What is Deep Learning (See Lecture 1 video and slides. Read Chapter 1 of textbook.) The Mathematical Building Blocks of Deep Learning (See Lecture 2 video for Part 1, video for Part 2 and slides. Read Chapter 2 of textbook.) Introduction to Keras and TensorFlow (See Lecture 3 video and slides. Read Chapter 3 of textbook.) Getting Started with Neural Networks: Classification and Regression (See Lecture 4 video for Part 1, video for Part 2, video for Part 3 and slides. Read Chapter 4 of textbook.) Fundamentals of Machine Learning (See Lecture 5 video and slides. Read Chapter 5 of textbook.) Working with Keras: A Deep Dive (See Lecture 6 video for Part 1, video for Part 2, video for Part 3 and slides. Read Chapter 6 and 7 of textbook.) Introduction to Deep Learning for Computer Vision (See Lecture 7 video for Part 1, video for Part 2, video for Part 3 and slides. Read Chapter 8 of textbook.) Advanced Deep Learning for Computer Vision (See Lecture 8 video for Part 1, video for Part 2 and slides. Read Chapter 9 of textbook.) Advanced Deep Learning for Computer Vision (See Lecture 8 video for Part 3, video for Part 4, video for Part 5 and slides. Read Chapter 9 of textbook.) Deep Learning for Timeseries (See Lecture 9 video for Part 1 and slides. Read Chapter 10 of textbook.) Deep Learning for Timeseries (See Lecture 9 video for Part 2, video for Part 3 and slides. Read Chapter 10 of textbook.) Deep Learning for Text (See Lecture 10 video for Part 1 and slides. Read Chapter 11 of textbook.) Deep Learning for Text (See Lecture 10 video for Part 2 , video for Part 3, video for Part 4 and slides. Read Chapter 11 of textbook.) Deep Learning for Text (See Lecture 10 video for Part 5, video for Part 6, video for Part 7 and slides. Read Chapter 11 of textbook.) Generative Deep Learning (See Lecture video on auto-encoder. Read Chapter 12 of textbook.) Generative Deep Learning (See Lecture video on VAE and GAN. Read Chapter 12 of textbook.) Generative Deep Learning (See Lecture video on GAN. Read Chapter 12 of textbook.) Generative Deep Learning (See Lecture video on GAN. Read Chapter 12 of textbook.) Best Practices for the Real World (See Lecture video on tuning hyperparameters. Read Chapter 13 of textbook.) Transfer Learning (See Lecture video on transfer learning) Transfer Learning (See Lecture video on transfer learning) Ensemble Learning (See Lecture video on ensemble learning, Part 1 of 3) Ensemble Learning (See Lecture video on ensemble learning, Part 2 of 3) Ensemble Learning (See Lecture video on ensemble learning, Part 3 of 3)
Updated Lecture Slides:
TBA
Statement: The Americans with Disabilities Act (ADA) is a federal anti-discrimination statute that provides comprehensive civil rights protection for persons with disabilities. Among other things, this legislation requires that all students with disabilities be guaranteed a learning environment that provides for reasonable accommodation of their disabilities. If you believe you have a disability requiring an accommodation, please contact Disability Services, currently located in the Disability Services building at the Student Services at White Creek complex on west campus or call 979-845-1637. For additional information, visit http://disability.tamu.edu.
“An Aggie does not lie, cheat or steal, or to tolerate those who do.” See http://aggiehonor.tamu.edu