An introduction to deep learning with Python and Pytorch. Covers optimization, neural network basics, convolutional neural networks, and advanced topics such as auto-encoders and generative adversarial networks.
© 2023 Arman Seyed-Ahmadi, Tomas Beuzen, Mike Gelbart, and Aaron Berk
Software licensed under the MIT License, non-software content licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) License. See the license file for more information.
Find Panopto lecture recordings here.
| # | Topic |
|---|---|
| 1 | Floating Point Errors |
| 2 | Optimization and Gradient Descent |
| 3 | Stochastic Gradient Descent |
| 4 | Introduction to Neural Networks & PyTorch |
| 5 | Training Neural Networks |
| 6 | Convolutional Neural Networks Part 1 |
| 7 | Convolutional Neural Networks Part 2 |
| 8 | Advanced Deep Learning |
There will be one lab assignment per week. We will follow the standard MDS lab deadlines.
Quizzes will be open book, meaning you may consult course materials, online sources, etc. However, communication with other people during the quiz is strictly forbidden. See the MDS quiz instructions here. For the dates/times of the quizzes, see the MDS calendar.
The Conda environment file for the course is here. To create the environment, run conda env create -f dsci572env.yml. Make sure to use the dsci572 kernel for your Jupyter notebooks.
- 3Blue1Brown Deep learning YouTube series
- Yann LeCun's NYU Deep Learning course
- Geoff Hinton's Coursera lectures
- CS231n: Convolutional Neural Networks for Visual Recognition (Stanford)
- Introduction to Deep Learning
- Deep Learning for Computer Vision (U of Michigan)
- Full Stack Deep Learning
- Neural Networks and Deep Learning
- Awesome Deep Learning
- Awesome ML Youtube channels
- Dive into Deep Learning
- Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville
- An Introduction to Statistical Learning: with Applications in R by Gareth James, Daniela Witten, Trevor Hastie, and Rob Tibshirani (Python code here and here).
- Artificial intelligence: a modern approach by Stuart Russell and Peter Norvig.
- Artificial Intelligence: foundations of computational agents by David Poole and Alan Mackwordth.
- Pattern Recognition and Machine Learning by Christopher Bishop.
- Probabilistic Machine Learning: An Introduction by Kevin Murphy.