[14:30] Coast-to-Coast Seminar: Deep Learning for Object Recognition and Motion Generation

Speaker: Dr. Geoffrey Hinton, Department of Computer Science, University of Toronto

I will describe how multiple layers of non-linear features can be learned one layer at a time from unlabeled images. The multiple layers of features form a good generative model of images and the highest level features are very good for object recognition. I will show how the same learning methods can be applied to high-dimensional sequential data to produce good generative models of people walking in many different styles.

NOTE: due to the size and complexity of delivering cross-country seminars, we regret we cannot support desktop AG connections for the Coast-to-Coast seminars

If you are planning to attend this seminar, ensure you have registered using the link provided at the top of this announcement. AG rooms will only be opened for these seminars where someone has indicated they plan to attend, and it is critical that we be aware of significant attendees in case a larger room needs to be booked.