UNIVERSITY OF HERTFORDSHIRE
		COMPUTER SCIENCE RESEARCH COLLOQUIUM

			     presents


       "Deep Learning for Object Recognition and Motion Generation"

                    Professor Geoffrey Hinton
                      (University of Toronto)


                    23 September 2009 (Wednesday)
			 Lecture Theatre E351 
		   Hatfield, College Lane Campus
			      3 - 4 pm


		   Everyone is Welcome to Attend



Abstract:

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.

---------------------------------------------------
Hertfordshire Computer Science Research Colloquium
http://homepages.feis.herts.ac.uk/~nehaniv/colloq