The Next Generation of Neural Networks
Sign in to YouTube
Sign in to YouTube
Sign in to YouTube
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.
Standard YouTube License
- 27:04 Nano, the Next Dimensionby EurActivFeatured 362,658
- 1:06:38 Polyworld: Using Evolution to Design Artificial Intelligenceby GoogleTechTalks 116,066 views
- 1:37:42 The Extended Mind: Recent Experimental Evidenceby Google Tech Talks 296,228 views
- 55:27 How Cybercriminals Steal Moneyby Google Tech Talks 135,004 views
- 1:29:54 Think faster focus better and remember moreRewiring our brain to stay younger...by Google Tech Talks 402,884 views
- 1:25:16 Lecture 10 - Neural Networksby California Institute of Technology 25,479 views
- 9 videos Play all boltzmann machinesby mac01021
- 56:31 The Secret History of Silicon Valleyby Google Tech Talks 219,222 views
- 56:27 Quantum Computing Day 1: Introduction to Quantum Computingby GoogleTechTalks 106,612 views
- 1:05:21 Transform Your Mind, Change Your Brainby GoogleTechTalks 524,992 views
- 48:54 Cognitive Neuroscience of Mindfulness Meditationby GoogleTechTalks 314,735 views
- 1:13:40 Quantum Computing Day 2: Image Recognition with an Adiabatic Quantum Computerby GoogleTechTalks 36,267 views
- 1:02:10 The Neuroscience of Emotionsby GoogleTechTalks 188,106 views
- 58:08 No Time to Thinkby Google Tech Talks 131,418 views
- 56:23 Tangible Functional Programmingby Google Tech Talks 41,611 views
- 1:02:13 The Cognitive and Computational Neuroscience of Categorization, Novelty-Detec...by GoogleTechTalks 51,737 views
- 1:02:52 Google Personal Growth Series: Mindsight: The New Science ofby Google Tech Talks 160,157 views
- 1:05:18 Recent Developments in Deep Learningby Google Tech Talks 47,562 views
- 2:41 Neural Network Demoby Matthew Robbins 33,416 views
- 1:10:16 Getting C++ Threads Rightby GoogleTechTalks 98,441 views
- Loading more suggestions...