IEEE Kansai Section第2回技術講演会

IEEE Kansai Section第2回技術講演会



``From bits to information: machine learning theory and applications''


Professor Tomaso Poggio (MIT AI Laboratory)

日時(Time & Date)

2000年1月14日(金) 13:00~14:30


NTTコミュニケーション科学基礎研究所 大会議室
〒619-0237 京都府相楽郡精華町光台2-4
Tel: 0774-93-5010
Fax: 0774-95-5015


I will outline some of our recent efforts at MIT to develop machines that learn. I will first sketch some of our work on statistical learning theory with recent theoretical results on the problem of classification and function approximation that connect regularization theory and Support Vector Machines. Our main application focus is classification (and regression) in various domains -- such as sound, text, video and bioinformatics. In particular, I will describe the recent evolution of a trainable object detection system for classifying objects such as faces and people and cars in complex cluttered images. We have also applied learning techniques to the domain of adaptive interfaces, both to analyze the user's facial expression and to synthesize a photorealistic speaking face.


Prof.Tomaso Poggio currently hold the Uncas and Helen Whitaker Professorship of Vision Sciences and Biophysics at the Department of Brain and Cognitive Sciences at MIT, and is also affiliated with MIT's Artificial Intelligence Laboratory. In addition, since 1993, he has been Co-Director of MIT's Center for Biological and Computational Learning (CBCL). His original training was as a theoretical physicist (he received a Ph.D. in Theoretical Physics from the University of Genoa in 1970) and his current research focuses on the application of new learning techniques to time series analysis, object recognition, adaptive control and computer graphics.

参加費 (Fee)

無料 (Free)

参加申込み先および連絡先 (Contact for registration and for further information)

619-288 京都府相楽郡精華町光台2-2
Yumiko Honjo (ATR MIS Labs.)
Tel: (0774) 95 1404
Fax: (0774) 95 1408


Copyright© IEEE Kansai Section All Rights Reserved