Training resources for an introduction to deep learning using Pytorch.
View the slides for this training here
Make sure that miniconda is installed.
conda env create -f environment.yml
In this lesson we will cover the basics of Artificial Neural Networks, the important math behind how and why they work and then do a quick survey of common types of ANNs and what they are used for.
We will begin to cover the basics of Pytorch and its core components. We will then look at how these components can be used to create a computation graph and how the Optim package allows us to backpropagate through it.
The notebooks provided in the repo show a simple example of using deep learning to solve the classification problem with the MNIST and FashionMNIST datasets.