Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning

Bay Area Vision Meeting (more info below)
Unsupervised Feature Learning and Deep Learning
Presented by Andrew Ng
March 7, 2011

ABSTRACT

Despite machine learning's numerous successes, applying machine learning to a new problem usually means spending a long time hand-designing the input representation for that specific problem. This is true for applications in vision, audio, text/NLP, and other problems. To address this, researchers have recently developed "unsupervised feature learning" and "deep learning" algorithms that can automatically learn feature representations from unlabeled data, thus bypassing much of this time-consuming engineering. Building on such ideas as sparse coding and deep belief networks, these algorithms can exploit large amounts of unlabeled data (which is cheap and easy to obtain) to learn a good feature representation. These methods have also surpassed the previous state-of-the-art on a number of problems in vision, audio, and text. In this talk, I describe some of the key ideas behind unsupervised feature learning and deep learning, describe a few algorithms, and present case studies pertaining.

The Bay Area Vision Meeting (BAVM) is an informal gathering (without a printed proceedings) of academic and industry researchers with interest in computer vision and related areas. The goal is to build community among vision researchers in the San Francisco Bay Area, however, visitors and travelers from afar are also encouraged to attend and present. New research, previews of work to be shown at upcoming vision conferences, reviews of not-well-publicized work, and descriptions of "work in progress" are all welcome.

• Category

  Science & Technology

[Mangalaiii]

Andrew Ng got bored of improving one algorithm so he decided to improve all algorithms at once...

[Lei Chen]

This talk is awesome; I can quickly pick up key points of deep-learning.

[hunarahmad]

I'm really grateful to this guy, he is responsible for me learning machine learning without teacher just by looking at his courses available online. I owe you much.

[plievone]

Hi, we have been thinking long and hard how to achieve this kind of unsupervised feature learning and deep learning in a natural way, and what kind of a worldview it suggests. Our suggestion is a kind of physical vitalism formalized as Enformation Theory, which is now summarized in a presentation accessible from my profile: watch?v=frOzDw1vtdw

[agamemnonc]

You might want to have a look at Chapter 6 of "Natural Image Statistics" by Hyvarinen, Hurri and Hoyer (p. 151 is your answer). It is freely available online.

Good luck

[masrab]

Andrew Ng has some key "features" that make him a very likable teacher!

[usazeez]

could you explain how the machine learns? after we extract the features!

[Han Zhao]

Awesome talk! Andrew keeps everything related to Deep learning as plain as possible.

[Yilun Wang]

awesome!