Build a Deep Learning Library

Tue 12 December 2017

In this fantastic bit of code-as-entertainment author Joel Grus walks through the building of a functional deep learning library. The video runs in under an hour and I was able to follow and code along in around two hours. He builds an actual library complete with loss and activation functions, and two sample programs that train models using the framework. The fact that it was so simple to build demystifies projects such as Tensorflow and can speed up your understanding of neural networks.

Category: Data Tagged: programming python machine learning