Posts

A Tutorial on the REINFORCE Algorithm
The setup for the general reinforcement learning problem is as follows. We’re given an environment $\mathcal{E}$ with a specified state space $\mathcal{S}$ and an action space $\mathcal{A}$ giving the allowable actions in each of those states.
Apr 18, 2018 5 min read Machine Learning, Reinforcement Learning
The Universal Approximation Theorem for Neural Networks
Any continuous function can be approximated to an arbitrary degree of accuracy by some neural network.
Mar 21, 2017 12 min read Machine Learning, Mathematics
The Universal Approximation Theorem for Neural Networks
A Primer on Gaussian Discriminant Analysis
We begin with a definition. Consider the following general classification problem: we are given a set of points ${x_1, \ldots, x_N} \in \mathbb{R}^d$. We seek to assign each of these to one of $K$ possible classes $C_k$.
Mar 19, 2017 3 min read Machine Learning
A Primer on Gaussian Discriminant Analysis