T81 558: Applications of Deep Neural Networks

Washington University in St. Louis

Instructor: Jeff Heaton

• Section 1. Spring 2026, Tuesday, 2:30 PM
  Location: LOUDERMAN, Room 00461

Course Description

Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as both input and output. Deep learning enables a neural network to learn hierarchies of information in a manner similar to the way the human brain functions. This course will introduce the student to classic neural network structures, Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), Gated Recurrent Units (GRUs), Generative Adversarial Networks (GANs), and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High-Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged on both graphical processing units (GPUs) and grids. The focus is primarily on the application of deep learning to problems, with some introduction to the mathematical foundations. Students will use Python and PyTorch to implement deep learning. It is not necessary to know Python prior to this course; however, familiarity with at least one programming language is assumed. This course will be delivered in a hybrid format, combining classroom and online instruction.

Objectives

1. Explain how neural networks (deep and otherwise) compare to other machine learning models.
2. Determine when a deep neural network would be a good choice for a particular problem.
3. Demonstrate understanding of the material through applied programming assignments and a Kaggle competition.

Syllabus

This syllabus presents the expected class schedule, due dates, and reading assignments.
Download current syllabus

Module	Content
Module 1 Meet on 01/12/2026	Module 1: Python Preliminaries 1.1 Course Overview 1.2 Introduction to Python 1.3 Python Lists, Dictionaries, Sets & JSON 1.4 File Handling 1.5 Functions, Lambdas, and Map/Reduce We will meet on campus this week (in-class meeting #1)
Module 2 Week of 01/19/2026	Module 2: Python for Machine Learning 2.1 Introduction to Pandas for Deep Learning 2.2 Encoding Categorical Values 2.3 Grouping, Sorting, and Shuffling 2.4 Apply and Map 2.5 Feature Engineering Module 1 Program due: 01/21/2026 Icebreaker due: 01/21/2026
Module 3 Meet on 01/26/2026	Module 3: PyTorch for Neural Networks 3.1 Deep Learning Overview 3.2 Introduction to PyTorch 3.3 Feature Vector Encoding 3.4 Early Stopping and Persistence 3.5 Sequences vs Classes Module 2 Program due: 01/27/2026 We will meet on campus this week (in-class meeting #2)
Module 4 Week of 02/02/2026	Module 4: Training for Tabular Data 4.1 K-Fold Cross-Validation 4.2 Training Schedules 4.3 Dropout 4.4 Batch Normalization 4.5 RAPIDS for Tabular Data Module 3 Program due: 02/03/2026
Module 5 Week of 02/09/2026	Module 5: CNN and Computer Vision 5.1 Image Processing 5.2 Convolutional Neural Networks 5.3 Pretrained Networks 5.4 Image Augmentation 5.5 YOLO Module 4 Program due: 02/10/2026
Module 6 Meet on 02/16/2026	Module 6: ChatGPT and Large Language Models 6.1 Transformers 6.2 ChatGPT API 6.3 LLM Memory 6.4 Embeddings 6.5 Prompt Engineering Module 5 Program due: 02/17/2026 We will meet on campus this week (in-class meeting #3)
Module 7 Week of 02/23/2026	Module 7: Image Generative Models 7.1 Generative AI 7.2 StyleGAN3 7.3 DeOldify 7.4 Stable Diffusion 7.5 DreamBooth Module 6 Program due: 02/24/2026
Module 8 Meet on 03/02/2026	Module 8: Kaggle 8.1 Introduction to Kaggle 8.2 Ensembles 8.3 Hyperparameters 8.4 Bayesian Optimization 8.5 Semester Kaggle Module 7 Program due: 03/03/2026 We will meet on campus this week (in-class meeting #4)
Module 9 Week of 03/16/2026	Module 9: Facial Recognition 9.1 Face Detection 9.2 Facial Features 9.3 Image Augmentation 9.4 Emotion Detection 9.5 Blink Efficiency Module 8 Program due: 03/17/2026
Module 10 Week of 03/23/2026	Module 10: Time Series in PyTorch Time Series Encoding Seasonality and Trend LSTM Time Series CNN Time Series Meta Prophet Module 9 Program due: 03/24/2026
Module 11 Week of 03/30/2026	Module 11: Natural Language Processing 11.1 NLP Overview 11.2 Hugging Face 11.3 Tokenizers 11.4 Datasets 11.5 Model Training Module 10 Program due: 03/31/2026
Module 12 Week of 04/06/2026	Module 12: Reinforcement Learning Gymnasium Q-Learning Stable Baselines Atari Games Future of RL
Module 13 Week of 04/13/2026	Module 13: Deployment and Monitoring 13.1 Denoising Autoencoders 13.2 Anomaly Detection 13.3 Model Drift 13.4 TPUs 13.5 Future Directions Kaggle Competition Closes: 04/19/2026 (midnight) Kaggle Assignment due in Canvas: 04/21/2026
Week 14 Week of 04/20/2026	Wrapup Discuss final Kaggle results and future directions of this technology.

Datasets

• Datasets can be downloaded here