# Tech Tuesday: Brainy Project Idea By [Continuations](https://continuations.com) · 2012-12-04 tech tuesday --- I ended last week’s [Tech Tuesday](http://continuations.com/tagged/tech_tuesday) with a [call for ideas](http://continuations.com/post/36671748437/tech-tuesday-programming-interim-review) for a sample project and got a couple of [suggestions](http://continuations.com/post/36671748437/tech-tuesday-programming-interim-review#disqus_thread).  Since then though I have come across a great idea for a project. And since I am teaching [my Skillshare class](http://www.skillshare.com/Bayesian-Probability-and-A-Theory-of-Life/435771181) today and therefore spending most of the morning hours reviewing my materials, I am keeping this post short to share the idea and its background. It’s simple: build a brain. OK, so that’s a vast overstatement. Really it will be more like simulating a bunch of neurons. But a lot has happened since I first read about neural networks in Rumelhart and McClelland’s [Parallel Distributed Processing](http://www.amazon.com/Parallel-Distributed-Processing-Explorations-Microstructure/dp/0262181207) (1986). And recent progress seems like there is real movement in the field. A lot of it seems to come from Canada.  There is [Geoff Hinton](http://www.cs.toronto.edu/~hinton/)’s work on [deep learning](http://en.wikipedia.org/wiki/Deep_learning) at the University of Toronto.  And separately [Chris Elisamith](http://arts.uwaterloo.ca/~celiasmi/)’s work on a [structurally realistic brain](http://www.nengo.ca/build-a-brain) with [visual recognition, memory and output](http://www.youtube.com/watch?v=P_WRCyNQ9KY).  Also, there was a recent paper by two Google engineers on learning to [recognize faces](http://research.google.com/pubs/pub38115.html) without an explicit training set. Building something even at the toy level here will be a fun excuse to read up a bit more on these recent developments. --- *Originally published on [Continuations](https://continuations.com/tech-tuesday-brainy-project-idea)*