TOPIC When Can Deep Networks Avoid the Curse of Dimensionality 
AREA Signal Analysis and Machine Intelligence  
SPEAKER Prof. Tomaso Poggio 
DATE 24 January 2017, Tuesday 
TIME 11am to 12pm 
VENUE E1-06-05, Engineering Block E1, Faculty of Engineering, NUS  
FEES No Charge 

In recent years, by exploiting progress in deep learning, artificial intelligence researchers have built impressive systems. Two of my former postdocs Demis Hassabis and Amnon Shashua are behind the two main success stories of AI: AlphaGo bettering human players at Go and Mobileye leading vision-based autonomous driving research. Some of the present excitement is due to realistic expectations for further progress, but a substantial effort in basic research is needed to develop a true science of intelligence.

In particular a mathematical theory of deep networks and of why they work as well as they do is still missing. I will briefly review some recent theoretical results on the approximation power of deep networks including conditions under which they can be exponentially better than shallow learning. A class of deep convolutional networks represent an important special case of these conditions, though weight sharing is not the main reason for their exponential advantage. Implications of a few key theorems are discussed, together with new results, open problems and conjectures.

Tomaso A. Poggio, is the Eugene McDermott Professor in the Dept. of Brain & Cognitive Sciences at MIT and the director of the NSF Center for Brains, Minds and Machines at MIT. He is a member of the Computer Science and Artificial Intelligence Laboratory and of the McGovern Brain Institute. He received the Laurea Honoris Causa from the University of Pavia for the Volta Bicentennial, the 2003 Gabor Award, the Okawa Prize 2009, the AAAS Fellowship and the 2014 Swartz Prize for Theoretical and Computational Neuroscience. A former Corporate Fellow of Thinking Machines Corporation and a former director of PHZ Capital Partners, Inc., is a director of Mobileye and was involved in starting, or investing in, several other high tech companies including Arris Pharmaceutical, nFX, Imagen, Digital Persona, Metaweb and Deep Mind. 

Host: Dr Feng Jiashi 

 | Back to seminar list |

All are welcome to attend these seminars.
Should you have any enquiries, please contact Ms Veronica Au , Tel: 6516 2109.