WAI102 Introduction to Neural Networks

WAI102 aims to introduce students to modern machine learning without forgetting the fundamentals. Inspired by Andrej Karpathy’s “spelled-out intro to neural networks” tutorial, in WAI102 we will learn how neural networks work from first principles by creating an automatic differentiation engine and implementing back-propagation.

Lastly, we’ll translate our implementation into a PyTorch equivalent implementation, developing a strong understanding of how modern machine learning frameworks work, and giving you the tools to start training your own models or implementing your own architectures!