Deep Learning has recently made headlines by winning matches of Go[1], running hotels [2], and, most importantly, identifying cats in YouTube videos [3]. The term has become synonymous, for some, with state of the art AI and deserves understanding. In this talk, I will demystify the phrase and give an overview of the underlying theory.Using real-world examples, I will cover the basics of a single perceptron and the complexities of back propagation and convolutional neural networks. I will illustrate why this method is now receiving widespread attention, and attempt to shed light on some of its current challenges.

Some potentially useful links:
[1] http://www.theverge.com/2016/3/9/11184362/google-alphago-go-deepmind-result
[2] http://arstechnica.com/gadgets/2016/03/ibm-watson-hilton-robot-connie/
[3] http://www.nytimes.com/2012/06/26/technology/in-a-big-network-of-computers-evidence-of-machine-learning.html