An alternative approach to sample points uniformly inside a circle.

Python implementations for Value & Policy iteration, two fundamental concepts of Reinforcement Learning.

How to work out the derivatives and implement the training loop in pure Python.

How can we make Entropy work for - and not against us.

Introduction to search algorithms - a fundamental for understanding artificial intelligence.

Recurrent Neural Networks are a fundamental concept to understand and offer strengths that uni-directional neural networks lack. How can we use one to predict stock prices?