YouTube home Comedy Week on YouTube
Upload

The Next Generation of Neural Networks

GoogleTechTalks GoogleTechTalks·1,782 videos
147,860
276,811
Like     Dislike 29

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to like GoogleTechTalks's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to dislike GoogleTechTalks's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to add GoogleTechTalks's video to your playlist.

Uploaded on Dec 4, 2007

Google Tech Talks
November, 29 2007

In the 1980's, new learning algorithms for neural networks promised to solve difficult classification tasks, like speech or object recognition, by learning many layers of non-linear features. The results were disappointing for two reasons: There was never enough labeled data to learn millions of complicated features and the learning was much too slow in deep neural networks with many layers of features. These problems can now be overcome by learning one layer of features at a time and by changing the goal of learning. Instead of trying to predict the labels, the learning algorithm tries to create a generative model that produces data which looks just like the unlabeled training data. These new neural networks outperform other machine learning methods when labeled data is scarce but unlabeled data is plentiful. An application to very fast document retrieval will be described.

Speaker: Geoffrey Hinton
Geoffrey Hinton received his BA in experimental psychology from Cambridge in 1970 and his PhD in Artificial Intelligence from Edinburgh in 1978. He did postdoctoral work at Sussex University and the University of California San Diego and spent five years as a faculty member in the Computer Science department at Carnegie-Mellon University. He then became a fellow of the Canadian Institute for Advanced Research and moved to the Department of Computer Science at the University of Toronto. He spent three years from 1998 until 2001 setting up the Gatsby Computational Neuroscience Unit at University College London and then returned to the University of Toronto where he is a University Professor. He holds a Canada Research Chair in Machine Learning. He is the director of the program on "Neural Computation and Adaptive Perception" which is funded by the Canadian Institute for Advanced Research.

Geoffrey Hinton is a fellow of the Royal Society, the Royal Society of Canada, and the Association for the Advancement of Artificial Intelligence. He is an honorary foreign member of the American Academy of Arts and Sciences, and a former president of the Cognitive Science Society. He received an honorary doctorate from the University of Edinburgh in 2001. He was awarded the first David E. Rumelhart prize (2001), the IJCAI award for research excellence (2005), the IEEE Neural Network Pioneer award (1998) and the ITAC/NSERC award for contributions to information technology (1992).

A simple introduction to Geoffrey Hinton's research can be found in his articles in Scientific American in September 1992 and October 1993. He investigates ways of using neural networks for learning, memory, perception and symbol processing and has over 200 publications in these areas. He was one of the researchers who introduced the back-propagation algorithm that has been widely used for practical applications. His other contributions to neural network research include Boltzmann machines, distributed representations, time-delay neural nets, mixtures of experts, Helmholtz machines and products of experts. His current main interest is in unsupervised learning procedures for neural networks with rich sensory input.

Loading icon Loading...

Loading icon Loading...

Loading icon Loading...

The interactive transcript could not be loaded.

Loading icon Loading...

Loading icon Loading...

Ratings have been disabled for this video.
Rating is available when the video has been rented.
This feature is not available right now. Please try again later.

Top Comments

  • Ganesh Iyer

    I am taking his coursera class! :D

    · 55

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Ganesh Iyer's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Ganesh Iyer's comment.
  • Reebokanonymous

    I wish they would show him interacting with the slides. It's sometimes difficult to follow what he's talking about because he's gesturing toward the slides, not describing the visuals, which is what we would need given our viewpoint.

    · 12

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Reebokanonymous's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Reebokanonymous's comment.

All Comments (223)

Sign in now to post a comment!
  • JohnZ622

    There's an extended tutorial on videolectures d o t net that has the gesturing.

    ·

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate JohnZ622's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate JohnZ622's comment.
    in reply to Reebokanonymous (Show the comment)
  • Ian MathWiz

    I'm not defending the fact that the other guy was trashing someone for being bald, but how is aging not a genetic disease? It's genetic, and it fits every characteristic of a disease that I know of.

    ·

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Ian MathWiz's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Ian MathWiz's comment.
    in reply to snowstroke1 (Show the comment)
  • Ian MathWiz

    "Neural Networks for Machine Learning" on Coursera. I don't know when they'll offer another run of it.

    ·

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Ian MathWiz's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Ian MathWiz's comment.
    in reply to lbf10 (Show the comment)
  • Nathan Nifong

    I'm having trouble finding the paper in which he actually published the proof of "adding another layer always increases the upper bound on prediction accuracy" It's a long shot, but could someone point me in the right direction?

    ·

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Nathan Nifong's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate Nathan Nifong's comment.
  • PetWolverine

    I want to shop in this 30-dimensional supermarket.

    ·

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate PetWolverine's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate PetWolverine's comment.
  • lbf10

    which class?

    ·

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate lbf10's comment.

    Sign in to YouTube

    Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to rate lbf10's comment.
    in reply to Ganesh Iyer (Show the comment)
  • Loading comment...
Loading...
Loading...
Working...
Sign in to add this to Watch Later