Learning Resources

List of Resources

There is a nearly endless list of resources for learning deep learning and machine learning more broadly. I've included some below, with my favorites marked by a Star.

Summary of Recommendations

Currently, my personal recommendation would be to do the following:
    If you have never done any machine learning at all and are just trying to get the basic ideas:
    Read Part I of Hands-On Machine Learning with Scikit-Learn. Develop some classical ML models predicting material properties from the Materials Project or similar database.
    For deep learning and modern AI techniques:
    For a high-level overview of what neural networks are and what they are doing, watch DL1—DL4 of 3Blue1Brown's  video series on neural networks , which covers neural networks, gradient descent, and backpropagation.
    For a practical approach, go through the  PyTorch  documentation, which itself has several tutorials. Start tinkering with PyTorch (and afterwards, you can start using  pytorch-geometric  or  dgl  for graph-based deep learning). Book suggestions are shown below if you prefer those.
    For a thorough yet accessible understanding of the theory behind deep learning, refer to  Understanding Deep Learning . It is excellent, without being overly technical. Chapters 1-10 and 13 are particularly valuable within the context of our group.

Machine Learning Fundamentals

Practical

  • Star Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow (on Dropbox)
  • This is by far my top-choice recommendation for learning about scikit-learn and more "classical" machine learning topics. That said, the latter half (i.e. the Keras and TensorFlow sections) is probably worth skipping in favor of other options. Chapters 1-4 are a perfect intro.
  • Star Machine Learning with PyTorch and Scikit-Learn (on Dropbox)
  • A widely recommended book that is very practical and includes some nice PyTorch content.
  •  Dive into Deep Learning 
  • This is an interactive book on deep learning with PyTorch, MXNet, JAX, and TensorFlow. If you want to understand a particular type of ML model in a given ML framework, this is a good reference.

Theoretical

  • Star  Understanding Deep Learning by Prince 
  • This is my favorite introductory book about deep learning. It strikes the perfect balance and provides the necessary context to understand what you will later be coding.