Source: /cirosantilli/deep-learning-is-mostly-matrix-multiplication

= Deep learning is mostly matrix multiplication

* https://petewarden.com/2015/04/20/why-gemm-is-at-the-heart-of-deep-learning/
* https://math.stackexchange.com/questions/41706/practical-uses-of-matrix-multiplication/4647422\#4647422

Notably, <convolution> can be implemented in terms of <GEMM>:
* https://stackoverflow.com/questions/64506489/what-does-it-mean-to-say-convolution-implementation-is-based-on-gemm-matrix-mul
* https://petewarden.com/2015/04/20/why-gemm-is-at-the-heart-of-deep-learning/