In the next ten years we will see data-driven technologies reconfigure systems in many different sectors, from autonomous vehicles to…

Breaking glass, barking dogs and crying babies – to computers it's all just noise. But a new wave of artificial intelligence is being taught how to listen in.

The algorithm can figure out when the word “moron” is used in good fun, and when a seemingly innocuous word like "animal" is being used to demonise people... (more…)

Inspired by both medieval siege engines and the recent release of Unity’s reinforcement learning SDK I taught a catapult to both identify, aim, and destroy a “missile” (in this case, a loving, rendered cylinder). The following post is full of fun gifs of... (more…)

In 2017 hope is that reinforcement learning will now prove useful in many realworld situations and will be interesting to see how effectively it can be deployed...