Most of the intuitions we build in 2D and 3D break in higher dimensions, a core problem for most machine learning problems. So where do they break? 31 Dec 2018 - 9 minute read

A writeup introducing KL divergence in the context of machine learning, various properties, and an interpretation of reinforcement learning and machine learning as minimizing KL divergence 07 Aug 2018 - 8 minute read

We introduce an interpretation of reinforcement learning as inference in a probabilistic graphical model called control-as-inference, which has driven many recent advances in deep RL. 12 Jun 2018 - 10 minute read

A simple and clean presentation of code for nearest neighbors, linear regression, and logistic regression. We've carefully written the code to make it as close to pseudocode as possible. 28 Jan 2018 - 5 minute read

In this article, we familiarize the reader with the basics of Tensorflow by constructing various machine learning models from linear regression to convolutional neural networks. 05 Jan 2017 - 10 minute read