Distinguished Lecture: Yann LeCun 'Predicting under Uncertainty: the Next Frontier in AI'

Abstract:

The rapid progress of AI in the last few years is largely the result of advances in deep learning and neural nets, combined with the availability of large datasets and fast GPUs.  We now have systems that can recognise images with an accuracy that rivals that of humans.  This is causing revolutions in several domains such as information access, autonomous transportation and medical image analysis. But all of these systems currently use supervised learning in which the machine is trained with inputs labelled by humans. The challenge of the next several years is to let machines learn from raw, unlabelled data, such as video or text. This is known as predictive (or unsupervised) learning.  Intelligent systems today do not possess "common sense", which humans and animals acquire by observing the world, by acting in it, and by understanding the physical constraints of it.  He will argue that the ability of machines to learn predictive models of the world is a key component of that will enable significant progress in AI.  The main technical difficulty is that the world is only partially predictable.  A general formulation of unsupervised learning that deals with partial predictability will be presented.  The formulation connects many well-known approaches to unsupervised learning, as well as new and exciting ones such as adversarial training.

Bio:

Yann LeCun is Director of AI Research at Facebook, and Silver Professor at New York University, affiliated with the Center for Data Science, the Courant Institute of Mathematical Science, the Center for Neural Science, and the Electrical and Computer Engineering Department.

He received the Electrical Engineer Diploma from ESIEE, Paris (1983), and a PhD in CS from Université P&M Curie (1987).  After a postdoc at the University of Toronto, he joined AT&T Bell Laboratories (Holmdel, NJ) in 1988, later becoming the head of the Image Processing Research Department at AT&T Labs-Research in 1996.  He joined NYU as a professor in 2003, following a brief period at the NEC Research Institute (Princeton). In 2012. He became the founding director of the NYU Center for Data Science. In late 2013, he was named Director of AI Research at Facebook, remaining on the NYU faculty part-time. He held a visiting professor chair at Collège de France in 2015-2016.

His current interests include AI, machine learning, computer perception, robotics, and computational neuroscience.  He is best known for his contributions to deep learning and neural networks, particularly the convolutional network model which is very widely used in computer vision and speech recognition applications.  He has published over 190 papers on these topics as well as on handwriting recognition, image compression, and dedicated hardware for AI.

LeCun is founder and general co-chair of ICLR and has served on several editorial boards and conference organizing committees. He is co-chair of the program Learning in Machines and Brains of the Canadian Institute for Advanced Research. He is on the  boards of IPAM and ICERM. He has advised many companies and co-founded startups Elements Inc. and Museami.  He is in the New Jersey Inventor Hall of Fame.  He is the recipient of the 2014 IEEE Neural Network Pioneer Award, the 2015 IEEE PAMI Distinguished Researcher Award, the 2016 Lovie Lifetime Achievement Award, and an Honorary Doctorate from IPN, Mexico.