GNN/ML 📚

GNNs books and courses:

• 🖥️ Introduction to Graph Neural Networks by Zak Jost
  

• 📘 Deep learning with graph-structured representations by Thomas Kipf 2020

• 📘 Geometric Deep Learning Grids, Groups, Graphs, Geodesics, and Gauges by Michael Bronstein et al., 2021

• 🎨 Graph Neural Networks for Novice Math Fanatic by Rishabh Anand

ML/DL

• Machine Learning, Zhi-Hua Zhou (2021)
  A compact mathematical explanation of the ML basics.

• AI and Machine Learning for Coders, Laurence Moroney (2020)
  A great collection of code implementations with TensorFlow, TensorFlow Lite, TensorFlow.js and many more.

• Designing Machine Learning Systems, Chip Huyen (2022)
  Just a very useful for ML- practitioners in industry.

• Deep Learning with Python, François Chollet (2nd edition 2021)
  The most understandable explanation of concepts in textual format, which is interesting to read. By the way, I’ll give the second copy to someone who’ll take good care of it.

• Deep Learning, Jan Goodfellow (2016)
  Comprehensive mathematical and conceptual explanation, insights for the open research fields.

• Deep Learning for Vision Systems, Mohamed Elgendy (2020)
  Detailed explanation for baseline’s Computer Vision backbones/architectures.

• Deep Learning for Coders with fastai and PyTorch, Jeremy Howard and Sylvain Gugger (2020)
  A view on Deep Learning from practitioners. Practical Data Ethics!

• Deep Learning: A Visual Approach, Andrew-Glassner (2021)
  Additional dimension for concept’s understanding.

• Computer Vision: Algorithms and Applications, Richard Szeliski (2nd edition, 2021)
  Constantly updated meta-survey.

• Interpretable Machine Learning, Christoph Molnar (2019)
  Survey, good starting point on the topic. Shapley Values.