Advanced Deep Learning  (Adv DL) –  CISC889013 – Spring 2024 – ISE Lab 205


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


Course Description:  This course will cover advanced deep-learning topics. We will start by very briefly covering the basics of neural networks and deep learning. We will cover multilayer perceptrons (MLPs), convolutional neural network (CNNs), and recurrent neural network (RNNs).

After this, out of many possible topics, the course will cover foundation models (transformers and large language models), latent variable models (variational autoencoders and diffusion models), generative adversarial networks, graph neural networks, and deep reinforcement learning. In each topic, we will cover the core theoretical concepts and the most prominent variations of implementing each type of model.

The class will include lecture sessions (covering the theory and variations), followed by paper reading sessions (covering papers picked by the students).

Topics [Tentative]
DateTopicKey models covered
2/6Logistics, DL BasicsMLP
2/8DL BasicsCNN
2/13DL BasicsRNN
2/15LLMs TheoryTransformer
2/20LLMs TheoryGPT, BERT, CLIP
2/22LLMs - Paper review
2/27LLMs - Paper review
2/29Variational models - Theory
3/5Variational models - TheoryBeta VAE, VQ-VAE
3/7Variational models - Paper review
3/12Variational models - Paper review
3/14Generative Adversarial Networks - TheoryWasserstein GAN, InfoGAN, CycleGAN, StyleGAN, BigGAN
3/19Diffusion Models - TheoryDDPM
3/21Diffusion Models - TheoryDALL-E
3/26No Class - Spring Break
3/28No Class - Spring Break
4/2Generative Models - Paper review
4/4Generative Models - Paper review
4/9Graph Neural Networks - Theory
4/11Graph Neural Networks - TheoryGCN, GAT
4/16Graph Neural Networks - Paper review
4/18Graph Neural Networks - Paper review
4/23Deep Reinforcement Learning - Theory
4/25Deep Reinforcement Learning - TheoryDQN, PPO
4/30Deep Reinforcement Learning - Paper Review
5/2Deep Reinforcement Learning - Paper Review
5/7Project Presentation
5/9Project Presentation
5/14Project 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 papers of your choice per topic
ProjectCode (+ short reprot)15
Knowledge retention mini-exam52 PM, May 19. Same Class
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. 

Final Exam