Build you a Skynet - An introduction to Machine Learning with Digit Recognisers

Want to build a Skynet (http://en.wikipedia.org/wiki/Skynet_(Terminator)), but don't know where to start?

In this brief introduction to Machine Learning (http://en.wikipedia.org/wiki/Machine_learning), we'll be writing our very own digit recognition systems using the simplest of ML algorithms, k-nearest neighbours (http://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm) (KNN). The goal of this exercise is to take images of handwritten single digits, and determine what those digits are.

Although it may sound tricky, it's actually fairly straightforward, and we'll have template solutions in several languages (C#, F#, Python, PHP, Ruby and Java) to help get us going. Any other language and you'll have to start from scratch, although it's still achievable in the time.

After that, you should be well on your way to creating your very own self-aware Global Digital Defence Network with which to destroy humanity! But if you get a re-programmed T-101 coming back through time and trying to stop you, you're on your own..

As usual, there will be pizza around 18:30 and a trip to the pub afterwards. Bring your laptop if you have one.