DATA 442 / 610 - Deep Learning and Neural Networks
This is the webpage for the Deep Learning and Neural Networks course held at William & Mary in Fall 2026.
Classes will be held in ISC 3342 on Monday and Wednesday from 2:00 PM to 3:20 PM
Course Description¶
This course teaches the foundation of Neural Networks and Deep Learning. Students entering into this course should have, at minimum, a background in data preprocessing, cleaning, manipulation, and dimensionality reduction within Python. Through an applied learning project, you will learn how to implement a machine learning project from design to implementation in the context of neural networks. Topics we will cover include the basic building blocks of neural networks, RNNs, convolutional networks and computer vision, backpropagation basics and strategies, and more. The course will utilize PyTorch.
Syllabus¶
Click here to download the Syllabus
Textbook¶
We will use the Deep Learning book by Goodfellow, Bengio, and Courville, which is available online for free at https://
Schedule¶
The course schedule will be updated regularly. Dates and topics may change as the semester progresses, so please check this regularly.
| Week | Day | Links | |
|---|---|---|---|
| 1 | Aug 26 | Course Introduction & History of Deep Learning | Slides |
| 2 | Aug 31 | Linear Classifiers & Perceptrons | |
| Sep 2 | Logistic Regression, Nonlinear Classifiers | ||
| 3 | Sep 7 | No class - Labor Day Holiday | |
| Sep 9 | Regularization, Optimization | ||
| Sep 11 | PS 0 Due (bonus): Getting started | ||
| 4 | Sep 14 | Optimization, Hyperparameter Tuning | |
| Sep 16 | No class | ||
| 5 | Sep 21 | Deep Neural Networks & Backpropagation, from scratch | |
| Sep 23 | Deep Neural Networks & Backpropagation, in PyTorch | ||
| 6 | Sep 28 | PyTorch AutoGrad | |
| Sep 30 | Image Data, Convolutional Layers | ||
| Oct 2 | PS 1 Due: Building a NN from scratch | ||
| 7 | Oct 5 | Convolutional Neural Networks | |
| Oct 7 | Convolutional Neural Networks (continued) | ||
| 8 | Oct 12 | Time series, Recurrent NNs | |
| Oct 14 | RNNs (continued) | ||
| 9 | Oct 19 | Graph NNs | |
| Oct 21 | Graph NNs (continued) | ||
| Oct 23 | PS 2 Due: CNNs and Image Data | ||
| 10 | Oct 26 | Transformers | |
| Oct 28 | Transformers (continued) | ||
| 11 | Nov 2 | Unsupervised deep learning, autoencoders | |
| Nov 4 | Probabilistic deep learning, variational autoencoders | ||
| Nov 6 | PS 3 Due: NNs and time-series data | ||
| 12 | Nov 9 | Variational autoencoders (continued) | |
| Nov 11 | Generative adversarial networks | ||
| 13 | Nov 16 | Generative adversarial networks (continued) | |
| Nov 18 | Contrastive representation learning | ||
| 14 | Nov 23 | TBD: Discuss Final Project | |
| Nov 24 | PS 4 Due: Generative models and representations | ||
| Nov 25 | No class - Thanksgiving Holiday | ||
| 15 | Nov 30 | Interpretability, GradCAM (tentative) | |
| Dec 2 | Physics-inspired deep learning (tentative) | ||
| Finals | Dec 7-15 | Final Project Report and Presentation |