UDL = Understanding Deep Learning
| Class # | Date | Topic | Reading | Assignment | Due |
| 1 | Tue, Jan 14 | Class Introduction | Syllabus UDL CH 1 | ||
| 2 | Thu, Jan 16 | Multi-Layer Neural Networks Background: Python Basics | UDL CH 2,3 Introduction to Python for Programmers (optional) | ||
| 3 | Tue, Jan 21 | Deep Neural Networks and Computing Gradients | UDL 4, 6.1 | ||
| 4 | Thu, Jan 23 | Backpropagation Algorithm | UDL 7 | ||
| 5 | Tue, Jan 28 | Our Computational Environment on Schooner a First Network Implementation | Be ready to ssh into Schooner and edit files UDL 6.3-6.6 | HW 0 | |
| 6 | Thu, Jan 30 | Instrumenting our Networks Deep Networks | Set up account on Weights and Biases UDL 8 | ||
| 7 | Tue, Feb 4 | Deep Networks II Expanding our First Network Implementation | n/a | HW 1 | HW 0 |
| 8 | Thu, Feb 6 | Regularization Techniques | UDL 9 | ||
| 9 | Tue, Feb 11 | Holistic Cross-Validation | n/a | ||
| 10 | Thu, Feb 13 | Convolutional Neural Networks: Introduction | UDL 10-10.1 | HW 2 | HW 1 |
| 11 | Tue, Feb 18 | Convolutional Neural Networks: Details | UDL 10.2-10.4 | ||
| 12 | Thu, Feb 20 | Convolutional Neural Networks Image Classification | UDL 5-5.1, 5.4-5.7,10.5-10.6 | ||
| 13 | Tue, Feb 25 | Data Handling in TensorFlow | tf.data: A Machine Learning Data Processing Framework | ||
| 14 | Thu, Feb 27 | Homework 3 introduction | n/a | HW 3 | HW 2 |
| 15 | Tue, Mar 4 | Autoencoders | n/a | ||
| 16 | Thu, Mar 6 | Residual Networks Tensorflow Model API | UDL 11 | ||
| 17 | Tue, Mar 11 | Model API II U-Nets and Semantic Segmentation | Understanding Semantic Segmentation with UNETs | HW 4 | |
| 18 | Thu, Mar 13 | Probabilistic Neural Networks | Adding Uncertainty to Neural Network Regression Tasks in the Geosciences | HW 3 | |
| - | Tue, Mar 18 | Spring Break | |||
| - | Thu, Mar 20 | Spring Break | |||
| 19 | Tue, Mar 25 | Variational Autoencoders | UDL 17 | ||
| 20 | Thu, Mar 27 | Recurrent Neural Networks: Introduction | Tutorial: Power of Recurrent Neural Networks | ||
| 21 | Tue, Apr 1 | Recurrent Neural Networks: Examples | Tutorial: Types of Recurrent Neural Networks | HW 5 | HW 4 |
| 22 | Thu, Apr 3 | Recurrent Neural Networks: Attention | UDL 12-12.2 | ||
| 23 | Tue, Apr 8 | Transformer Networks I | UDL 12.3-12.6 Transformer: Self Attention | ||
| 24 | Thu, Apr 10 | Transformer Networks II | UDL 12.7-12.9 The Illustrated Transformer | HW 6 | HW 5 |
| 25 | Tue, Apr 15 | Visual Transformers | UDL 12.10-12.11 | ||
| 26 | Thu, Apr 17 | Diffusion Models | UDL 18 | ||
| 27 | Tue, Apr 22 | Diffusion Models II | TBD | HW 7 | HW 6 |
| 28 | Thu, Apr 24 | Generative Adversarial Networks | UDL 14, 15-15.7 | ||
| 29 | Tue, Apr 29 | Normalizing Flows | UDL 16 | ||
| 30 | Thu, May 1 | Deep Learning: Bigger Picture | UDL 20 | HW 7 | |
| Tue, May 6 | No final exam | n/a |
Back to Main Web Page