Professor Yoshua Bengio, Université de Montréal
"From Deep Learning to AI"
Abstract: Research in artificial intelligence has known surprising breakthroughs in recent years, thanks in great part to progress in deep learning. So much so that some people now express fears about the potential consequences, whereas just a few years ago the hope for reaching human-level intelligence was gone from most radar screens. Deep learning methods are approaches to machine learning, which allow computers to obtain the knowledge required for intelligent behaviour through learning from examples. More specifically, deep learning algorithms are based on learning multiple levels of representation. Deep learning has already been extremely successful in speech recognition, computer vision and is quickly rising as a major tool for natural language processing. We motivate deep learning and review recent theoretical results on their expressive power and their optimization landscape. We close on some of the exciting challenges ahead on fronts such as unsupervised learning, especially via deep generative models, the role of attention mechanisms and natural language understanding.
Bio: Yoshua Bengio is Full Professor of the Department of Computer Science and Operations Research at the Université de Montréal, head of the Montréal Institute for Learning Algorithms (MILA),CIFAR Program co-director of the CIFAR Neural Computation and Adaptive Perception program and Canada Research Chair in Statistical Learning Algorithms. His main research ambition is to understand principles of learning that yield intelligence. He teaches a graduate course in Machine Learning (IFT6266) and supervises a large group of graduate students and post-docs. His research is widely cited (over 40,000 citations found by Google Scholar in mid-2016, with an H-index of 84). He is currently action editor for the Journal of Machine Learning Research, associate editor for the Neural Computation journal, editor for Foundations and Trends in Machine Learning, and has been associate editor for the Machine Learning Journal and the IEEE Transactions on Neural Networks. Yoshua Bengio was Program Chair for NIPS’2008 and General Chair for NIPS’2009 (NIPS is the flagship conference in the areas of learning algorithms and neural computation). Since 1999, he has been co-organizing the Learning Workshop with Yann Le Cun, with whom he has also created the International Conference on Representation Learning (ICLR).He has also organized or co-organized numerous other events, principally the deep learning workshops and symposia at NIPS and ICML since 2007.
The lectures are free and everyone is welcome to attend.
ECE Distinguished Lectures Series website