Welcome to DATA621 - Neural Networks and Deep Learning#
(last update 12/3/2024)
This is the landing page for the course on Neural Networks and Deep Learning held at William & Mary during Fall 2024

Important
The lectures will take place at the Integrated Science Center, room 2291
Synopsis: Neural networks and deep learning have revolutionized the field of artificial intelligence, enabling breakthroughs in image recognition, natural language processing, and more. This course will explore the foundational concepts and practical applications of neural networks, covering how to build them from scratch as well as utilizing popular deep learning libraries. Students will delve into various architectures, including Multilayer Perceptrons (MLP), Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), Graph Neural Networks (GNN), and more recent advancements. By the end of the course, participants will have hands-on experience and a deep understanding of both the theory and practice of neural networks and deep learning.
This course is based on the following references: [BGC17, KK22, RLM22]
Syllabus
Schedule
Assignments
[Pre-flight] Intro to Modeling
[Pre-flight] Introduction to git
[Pre-flight] Using VS-Code
[8/29/2024] Introduction to High Performance Computing (HPC)
[9/3/2024] Linear Classifiers
[9/5/2024] Gradient Descent, stochastic GD, Logistic Regression and Other classifiers
[9/10/2024] Building Training Datasets
[9/12/2024] Model Evaluation, Hyperparameter Tuning: Examples and Discussion
[9/17/2024, 9/19/2024] Building Multi-Layer Neural Networks from scratch + discussion on assignment
[9/24/2024] Building Multi-Layer Neural Networks with PyTorch
[9/26/2024] PyTorch and Autograd
[10/1/2024, 10/3/2024, 10/8/2024] CNN with PyTorch
[10/15/2024, 10/17/2024] Explainable AI using Grad-CAM for visual explanations
[10/22/2024, 10/24/2024] Recurrent Neural Network
[10/29/2024, 10/31/2024, 1/7/2024] Generative Adversarial Networks
[11/24/2024] Graph Neural Networks
[12/03/2024, 12/05/2024] Transformers
Additional resources
Credits: Material on git, VS-Code, and HPC prepared by K. Suresh