This material is not intended to be a full course on machine, deep learning, or neural networks, and is meant to introduce basic Pytorch functionality based on a number of examples. Pre-requisites are:
- Basic Linear Algebra
- Experience with Python Programming and the scientific python stack (Numpy, Matplotlib, ...) is recommended.
- Some familiarity with Neural Networks, Optimization, Convolutional Neural Networks and their concepts.
All code is meant to be run on Google Colab and was built on Pytorch 1.0.
| Session | Exercise (Colab) | Solutions (Colab) |
|---|---|---|
| Getting Started: Google Colab and Logistics | Exercise  |
|
| Session 1: Pytorch, Automatic Differentiation, Neural Nets | Exercise |
Solutions |
| Session 2: Training Deep Neural Networks | Exercise |
Solutions |
| Session 3: Convolutional Neural Networks | Exercise |
Solutions |
| Project: The Seismic-NIST Dataset | Dataset | Benchmark |