Why do Convolutional Neural Networks work so well?

While deep learning has existed since the 1970s, it wasn't until 2010 that deep learning exploded in popularity, to the point that deep neural networks are now used ubiquitously for all machine learning tasks. The reason for this explosion is the invention of the convolutional neural network. This remarkably simple architecture allowed neural networks to be trained on new kinds of data which were previously thought impossible.

In this video I discuss what a convolutional neural network is, why it is needed, what it can and cannot do, and why it works so damn well.

00:00 Intro
01:18 The curse of dimensionality
06:39 Convolutional neural networks
13:09 The spatial structure of images
15:06 Conclusion