Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning

A good intro page with lots of links: [LINK] A lot of the newest work is under a few different names: "deep learning", "convolutional deep networks", "unsupervised feature learning", etc. Here's a great talk by Andrew Ng of Stanford, who's a recent convert to this area: [VIDEO] (Note that this is quite a one-sided view of things, but it does convey the excitement of deep-learning researchers and the potential of what might be possible.) Although I'm not in deep learning myself (I'm a computer vision researcher), here's a TL;DR as I understand it: rather than having people in specific domains such as computer vision or speech processing create their own features, the idea is to take raw inputs (pixels in the case of images) and train multi-layer neural net architectures that "learn" the relevant higher-level features in an unsupervised way (i.e., without labeled training data). Some of these seem to be pulling out interesting features and perform competitively on a few benchmarks in vision and other fields. I'm not sold on this yet, because it seems like the complexity of designing features has merely been traded in for the complexity of designing different learning architectures, but it's certainly becoming quite popular these days (mostly led by Geoff Hinton of Toronto, Yoshua Bengio of Montreal, and Yann LeCunn of NYU).

This seems very related to this [VIDEO] speak by Andrew Ng. It is a 40min speak, but he explains very simply how all this works for images and some examples about the audio case. It is incredible how using this deep learning techniques we can teach this "neural networks" to recognize such complicated patterns. It is like reverse engineering the brain's algorithms. BTW I took his Coursera's course about Machine Learning and it was great! I also recommend it A LOT to gather basic ML knowledge.

Check out this (awesome) talk: [VIDEO] There are a number of areas in which unsupervised feature learning outperforms the hand-programmed models we have been fine-tuning for decades.

Thanks for pointing this out. Here is a similar awesome by Andrew Ng [VIDEO] who teaches the original Coursea Machine Learning class.

the one overview I've found the most useful is [VIDEO] (Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning by Andrew Ng in April 2011).

Andrew Ng has a fantastic example of visualizing deep belief nets: [VIDEO] The example starts at about 18:20. You really need to have watched the previous material to understand it, but the basic idea is that he's plotting the hierarchy of features learned by successive layers of a deep neural net (a sparse autoencoder, IIRC, it's been a while since I watched it).

Here is a more in-depth presentation he gave on the same subject at a Google Tech Talk: [VIDEO] (April 11, 2011)

They kind of hint at it in the article, but sounds like automatic feature detection really helped here. That's really the future (or present): learning algos discovering better features automatically, significantly cutting down the labor involved in feature engineering. Pretty neat. Here's a video talking about current research into this at Stanford: [VIDEO]