The Next Generation of Neural Networks

Get the latest Flash player

googletechtalks
December 04, 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...

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.

Category: People & Blogs

Tags:

google techtalks techtalk engedu talk talks googletechtalks education

More From: googletechtalks

Next Generation All-IP Telecom Networks: Qualit...

38,135 views

Quantum Computing Day 1: Introduction to Quantu...

48,800 views

Artificial intelligence and digital media

21,061 views

Faster HTML and CSS: Layout Engine Internals fo...

18,919 views

The Cognitive and Computational Neuroscience of...

24,484 views

Learning 3D Models from a Single Still Image

16,878 views

Intelligence in Wikipedia

17,851 views

Tangible Functional Programming

23,322 views

Visual Perception with Deep Learning

15,198 views

Aging of the Other Genome: A Decisive but Ambit...

23,540 views

Large image databases and small codes for objec...

8,835 views

"Science and the taboo of psi" with Dean Radin

69,293 views

A Possible Future of Software Development

28,710 views

Personal Growth Series: Karl Deisseroth on Crac...

13,321 views

The Web That Wasn't

36,696 views

Quantum Computing Day 2: Image Recognition with...

20,817 views

Cognitive Neuroscience of Mindfulness Meditation

97,818 views

Wuala - a distributed file system

54,696 views

Bayesian nonparametrics in document and languag...

5,445 views

Polyworld: Using Evolution to Design Artificial...

70,400 views

See all 1193 videos

Play All Stop Autoplaying | Play Next

QuickList(0)

Clear | Save

356 ratings

108,446 views

Favorite

Playlists

Flag

Want to add to Favorites? Sign In or Sign Up now!

Want to add to Playlists? Sign In or Sign Up now!

Want to flag a video? Sign In or Sign Up now!

Statistics & Data

Video Responses (0)

This video has no Responses. Be the first to Post a Video Response.

Text Comments (73) Options

Dirtfire (1 week ago)

Comment removed by author

shorty0802 (2 months ago) Show Hide

Marked as spam

In 22:00, After presenting some number to the neural network. Shouldnt shouldnt it change the weights so the data matches more to one number, and when it runs backwards, why does it change it weights ?

kilianguntner (2 months ago) Show Hide

Marked as spam

Interesting! :) //K

bluesrunthegame (3 months ago)

Comment removed by author

Comment(s) marked as spam Show

blablablag (5 months ago) Show Hide

Marked as spam

36:20 lol @ the 30-dimensional supermarket :D

UnowMe00 (5 months ago) Show Hide

Marked as spam

lol, great talk! the jokes are ok, he is self-ironical also...

I love the idea with the random noise on ravines to form abstractions of perception and reversely generation! It's simply elegant...

McYxee (5 months ago) Show Hide

-10

Marked as spam

mallardvasey (3 months ago) Show Hide

Marked as spam

Who cares?The only thing that matters is what he is saying, which is fascinating (if not entirely novel). If he wants to make a few gentle jokes to leaven things, more power to him.

Showing 10 of 73 comments

Show More Comments

View All 73 comments

Would you like to comment?

Join YouTube for a free account, or sign in if you are already a member.

YouTube	Programs	Help	Policy	Discover
Contact Us	Advertising	Get Help	Privacy Policy	YouTube on Your Phone
YouTube Store	Developers	YouTube Handbook	Terms of Service	YouTube on Your Site
Press Room	Partnerships	Community Help Forums	Copyright Notices	YouTube on Your TV
Business Blog	Content Management	Safety Center	Community Guidelines	YouTube RSS Feeds
YouTube Blog		Creator's Corner		TestTube

Add YouTube to your Google homepage

Current Location: Italy Show locations

The Next Generation of Neural Networks

More From: googletechtalks

QuickList(0)

Related Videos

Statistics & Data

Video Responses (0)

Text Comments (73) Options

Would you like to comment?