## Sticky Post – Read this first. Categories and Links in Mathemafrica

The navigability of Mathemafrica isn't ideal, so I have created this post which might guide you to what you are looking for. Here are a number of different categories of post which you might like to take a look at: First year mathematics notes and resources (particularly for the University [...]

## Inverse Reinforcement Learning: Guided Cost Learning and Links to Generative Adversarial Networks

Recap In the first post we introduced inverse reinforcement learning, then we stated some result on the characterisation of admissible reward functions (i.e reward functions that solve the inverse reinforcement learning problem), then on the second post we saw a way in which we proceed with solving problems, more or [...]

## Maximum Entropy Inverse Reinforcement Learning: Algorithms and Computation

In the previous post we introduced inverse reinforcement learning. We defined the problem that is associated with this field, which is that of reconstructing a reward function given a set of demonstrations, and we saw what the ability to do this implies. In addition to this, we also saw came [...]

## Inverse Reinforcement Learning: The general basics

Standard Reinforcement Learning The very basic ideas in Reinforcement Learning are usually defined in the context of Markov Decision Processes. For everything that follows, unless stated otherwise, assume that the structures are finite. A Markov Decision Process (MDP) is a tuple $latex (S,A, P, \gamma, R)$ where the following is [...]

## Correlation vs Mutual Information

This post is based on a (very small) part of the (dense and technical) paper Fooled by Correlation by N.N. Taleb, found at (1) Notes on the main ideas in this post are available from Universidad de Cantabria, found at (2) The aims of this post are to 1) introduce mutual [...]

## The Res-Net-NODE Narrative

Humble Beginnings: Ordinary Differential Equations The story begins with differential equations. Consider $latex f$ such that $latex f:[0,T]\times \mathbb{R}^n\to \mathbb{R}^n$ is a continuous function. We can construct a rather simple differential equation given this in the following way. We let $latex \begin{cases} {y'(t)}=f(t,y(t))\\ y(0)=y_0\in \mathbb{R}^n \end{cases} $ A solution to [...]

## Scaled Reinforcement Learning: A Brief Introduction to Deep Q-Learning

This blog post is a direct translation of a talk that was given by the author on the 17th of February 2020. The ideas was to very briefly introduce Deep Q-Learning to an audience that was familiar with the fundamental concepts of reinforcement learning. If the person reading this is [...]

## Curves for the Mathematically Curious – an anthology of the unpredictable, historical, beautiful and romantic, by Julian Havil – a review

NB I was sent this book as a review copy. From Princeton University Press. What a beautiful idea. What a beautiful book! In studying mathematics, one comes across various different curves while studying calculus, or number theory, or geometry in various forms and they are asides of the [...]

## The Objective Function

In both Supervised and Unsupervised machine learning, most algorithms are centered around minimising (or, equivalently) maximising some objective function. This function is supposed to somehow represent what the model knows/can get right. Normally, as one would expect, the objective function does not always reflect exactly what we want. The objective [...]

## Tales of Impossibility – The 2000 year quest to solve the mathematical problems of antiquity, by David S. Richeson – a review

NB I was sent this book as a review copy. From Princeton University Press. Four impossible puzzles, all described in detail during the height of classical Greek Mathematics. All simple to define and yet so tempting that it has taken not only the brain power of many, many thousands [...]

## Simpson’s Paradox

Introduction A key consideration when analysing stratified data is how the behaviour of each category differs and how these differences might influence the overall observations about the data. For example, a data set might be split into one large category that dictates the overall behaviour or there may be a [...]