Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning

Channel:Google TechTalks · Length:48:10 · Published:2011-04-11 · Views:122987

Watch on YouTube

Summary

Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.

Why HN recommends it

HN commenters recommended it for years as a simple, exciting overview of the deep learning wave.

he explains very simply how all this works for images and some examples about the audio case. — HN, 2012

Machine learning & deep learning · Computer vision, speech & NLP

Subtitles (excerpt)

>> The first speaker is Andrew Ng and he's going to speak about "Unsupervised Feature Learning and Deep Learning." He's done lots and lots of great work and there's many things I could say but he said I should just keep it short and let him get up and give his talk because Research Interesting Machine Learning, Reinforcement Learning and Robotic Control and he'll share some of his work with us now. >> NG: Okay. Thanks, Allie. Tell you a bit about Unsupervised Feature Learning and Deep Learning. And I know that most of us in this room care primarily about computer vision and--but I'm going to develop these ideas using computer vision as was examples drawn from audio and text. Let's say you want to do image classification, right. What you do is you take an image and you feed it to learning algorithm and it learns to classify it as a motorcycle or not. All of us notes pictures and read it like this, what we do is we actually take the image and we construct a feature representation and it's that feature representation that we feed to, say, a super vector machine. More generally, this type of pipeline is pervasive in computer vision and in other domains where there's a sub--low-level feature is what we

On Hacker News

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). — michael_nielsen, 2013-04
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). — pilooch, 2012-11
Thanks for pointing this out. Here is a similar awesome by Andrew Ng [VIDEO] who teaches the original Coursea Machine Learning class. — FrojoS, 2012-08
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… — brutuscat, 2012-06
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. — kevin1024, 2012-06

Related videos