Saturday 10:40 a.m.–11:20 a.m.

Brainstorm your own Artificial Neural Network in Python

Holger Spill

Audience level:


Have you ever wanted to teach your computer how to recognise handwritten digits? The difficulty of visual pattern recognition becomes apparent when writing a computer program to recognize shapes. What seems easy when we do it ourselves quickly becomes complex when done programmatically. This talk will explore some of the concepts of Neural Networks with Brainstorm – an open-source Python library.


You don't need a PhD in math to run some machine learning algorithms in python and get some understanding of what’s going on. Just have fun with what you can do!

No previous knowledge is assumed and concepts are introduced in as much detail as is needed to be able to follow the walk-through of a ‘Hello World’ neural network setup. Brainstorm, the key library in this presentation, was open-sourced in October 2015. It was developed at the Swiss AI Lab IDSIA by PhD students Klaus Greff and Rupesh Srivastava (

Basically, I will strive to present the topic in a way that I wish I had come across when I was starting out.

The high-level outline of the talk is: