Here I list some important sources that have helped me to better understand deep learning, machine learning, and AI for Materials. The sources are rather disorganized; perhaps I will try to organize them in the future.

• What's a tensor? 

• PyTorch basic tutorials (Look into the Quickstart and Tensor sections)

• Read What is torch.nn, really?, by Jeremy Howard (fast.ai) for a deeper understanding of how one of the most important modules in PyTorch works. 

• Loading and saving documentation on the PyTorch website to become more familiar with the different saving and loading options in PyTorch. 

• Read wikipedia page for Gradient descent. 

• Read the article Gradient Descent Unraveled by Manpreet Singh Minhas - highly recommended. 

• Watch the video Gradient descent, how neural networks learn by the youtube channel 3Blue1Brown. 

• What is backpropagation really doing? watch the video by the youtbue channel 3Blue1Brown

• Gradient descent with momentum by Rauf bhat. 

• Read wikipedia page for different activation functions. 

• Great resource from MIT 6.S191 Introduction to Deep Learning 

• Summer school on Statistical Physics & Machine Learning 

• Machine Learning for Materials (MATE70026)

• Andrew White's Deep learning for molecules & materials (DMOL)

• Greg Landrum's RDKit Blog