Biffures

Biffure #1: Hearthstone, Verhulst & exponential functions

Fermat’s little theorem

An “etymological” and visual exploration of Fermat’s little theorem, one of…

RL Course by David Silver (Lectures 8 & 9)

We finish the series of lectures by David Silver and move on to implementation exercises

Lecture 8: Integrating Learning and Planning

RL Course by David Silver (Lectures 5 to 7)

This is day 45 of my 60-day reinforcement learning challenge, and we continue the series of lectures by Deepmind’s David Silver.

Network sparsity and rectifiers

Where we learn why, despite being amazing on their own, linear and…

All the single neurons

Where we learn that it takes one neuron to solve multilinear regressions and logistic regressions, which I thought were pretty advanced back in university

Reinforcement learning, from 0 to something in 60 days

In this series, I will attempt to learn something about reinforcement learning in a limited period of time, after work hours, with the intent to have a somewhat performant system built by the end of that period. A system that plays…

Part 5: Hashing with SHA-256

An overview of SHA-256, a standard secure hash function, as described in…