Browse posts by tag
The inductive-biases series is now a ten-episode animated playlist: every architecture is a bet about the world, and the bet is the bias. No free lunch first, then each architecture read as its assumptions, graded on one scorecard.
Perspective of deep learning from applied math. Bridges math with neural nets.
Free open-source deep learning book with code and math integrated. Interactive deep learning resource with runnable code.
Seminal blog post demonstrating the power of character-level RNNs. Shows Shakespeare generation, Wikipedia generation, LaTeX generation, and Linux kernel code generation. The visualizations of LSTM cells are particularly illuminating.