Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
“The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free.”
fast.ai “Making neural nets uncool again”
I had no idea Jeremy Howard, the CEO of fast.ai, was such a bad ass! He seems like a really cool dude. I watched the video of the AI podcast where he appears. He’s critical of academia which focuses on getting many publications/citations leading to publishing papers on topics which are recognizable and popular over what’s practical and useful. He says he doesn’t like writing papers and has only written one. He realized there weren’t many papers written about transfer learning in NLP, so he trained a model himself and smashed the scores on the benchmark for 6 tests. He developed the model and his friend, Sebastian Ruder, wrote the paper (Universal Language Model Fine-tuning for Text Classification). He recognized a gap in medicine which can be helped with deep learning. His hope with fast.ai is to make deep learning accessible to people in different domains so deep learning can have a wide ranging and powerful impact.
“What are your recommendations for self-studying machine learning?” A Quora answer by Yann LeCunn