Advanced Deep Learning  (Adv DL) –  CISC889011 – Spring 2023 – Purnell  Hall 324B


Prerequisite: Formally, CISC681; practically, any 400+-level courses in AI/ML


Course Description:  This course will cover advanced deep-learning topics. Out of many possible topics, the course will cover generative adversarial networks, latent variable models (VAEs), graph neural networks, deep reinforcement learning, and foundation models (transformers). The class will include lecture sessions (covering the methods and examples), followed by paper reading sessions (covering papers picked by the students). 

2/9Latent Variable Models – Theory
2/14Latent Variable Models – Basic VAEs
2/16Latent Variable Models - Paper Review 1
2/21Latent Variable Models – VAE Types
2/23Latent Variable Models - Paper Review 2
2/28Generative Models - Theory
3/2No Class
3/7Generative Models - Variations
3/9Generative Models - Applications
3/14Generative Models - Paper Review 1
3/16Generative Models - Paper Review 2
3/21Graph Neural Networks - Theory
3/23Graph Neural Networks - Variations and Applications
3/28No Class - Spring Break
3/30No Class - Spring Break
4/4Graph Neural Networks - Paper Review 1
4/6Graph Neural Networks - Paper Review 2
4/11Deep Reinforcement Learning - Theory
4/13Deep Reinforcement Learning - Variations and Applications
4/18Deep Reinforcement Learning - Paper Review 1
4/20Deep Reinforcement Learning - Paper Review 2
4/25Transformer-based Models - Theory
4/27Transformer-based Models - Variations
5/2Transformer-based Models - Paper Review 1
5/4Transformer-based Models - Paper Review 2
5/9Project Preparation - No Class
5/11Project Presentation
5/16Project Presentation
Learning Objectives
  • For the five major deep learning topics covered in class, be familiar with the following aspects:
    • Theoretical (math) basis
    • Algorithmic implementation and considerations
    • Major applications and success stories
    • Current SOTA methods
    • Any possible societal impacts and implications
    • Future ways of extension and research 

Reading assignments402 paper of your choice per topic
ProjectCode (+ short repot)15
Knowledge retention mini-exam51 PM, May 22. In Class, Open Book
Peer-review10For grading classmates
A90 and overB-70 to 75D+50 to 55
A-85 to 90C+65 to 70D45 to 50
B+80 to 85C60 to 65D-40 to 45
B75 to 80C-55 to 60FBelow 40
Ed Discussion

We will use Ed for ALL of the class communications. The system is highly catered to getting you to help fast and efficiently from classmates, the TA, and myself. Rather than emailing questions to the teaching staff, I encourage you to post your questions on Ed. Check for existing questions, and consider answering your classmates’ questions.