Geoffrey Hinton on Deep Learning and its Applications
Come hear one of the world’s leading computer scientists speak on deep learning and how neural networks, or learning machines, will change our world.
Geoffrey Hinton is an emeritus distinguished professor in the department of computer science in the Faculty of Arts & Science at UofT and vice-president engineering fellow at Google. Hinton’s research into artificial neural networks has been ground-breaking and his neural networks startup, DNN research, was acquired by Google in 2013.
Deep Learning and its Applications
Deep neural networks that have many layers of feature detectors between the input and the output are much better than hand-engineered systems at tasks like speech recognition, object recognition, and machine translation. Using a simple learning procedure that Hinton will explain, these networks create their own internal representations of the input data. The success of deep learning means that there are now two very different ways to get computers to do what you want: write a complicated program or show lots of examples of the behaviour you want to a simple learning procedure.
Geoffrey Hinton received his PhD in Artificial Intelligence from Edinburgh in 1978. After five years as a faculty member at Carnegie-Mellon he became a fellow of the Canadian Institute for Advanced Research and moved to the Department of Computer Science at the University of Toronto where he is now an emeritus distinguished professor. He is also a VP Engineering Fellow at Google Toronto. Geoffrey Hinton was one of the researchers who introduced the backpropagation algorithm and the first to use backpropagation for learning word embeddings. His research group in Toronto made major breakthroughs in deep learning that revolutionized speech recognition and object classification. In 2010 he won the NSERC Herzberg Gold Medal which is Canada’s top award in Science and Engineering.
Friday, March 31 from 12:00-1:00pm
Goldring Centre for High Performance Sport
100 Devonshire Place