We are very pleased to announce a research presentation by Dr. Simon Thorpe on Wednesday, November 11.
Has object vision been solved?
Simon Thorpe, CerCo (Brain and Cognition Research Center), Toulouse, France
The ability of humans to identify and categorize objects in complex natural scenes has long been thought to be beyond the capacities of artificial vision systems. However, recent progress in Deep Learning and Convolutional Neural Networks has demonstrated that simple feed-forward processing architectures composed of less than 10 layers of neurons can achieve human levels of performance in object recognition tasks. It is interesting to note that such processing architectures have a very similar structure to the primate visual system. Could it be that we are close to understanding how our brains recognize stimuli? I will argue that the main problem with the current state of the art in computer vision is that the learning procedures used are totally unrealistic. Essentially, building such a system requires hundreds of millions of training cycles of supervised learning. By contrast, our own visual systems can learn new stimuli in a few tens of presentations. I will suggest that more biologically realistic learning mechanisms based on spike-based processing and Spike Time Dependent Plasticity (STDP) may be much closer to the way our own visual systems operate, and allow our visual systems to learn about objects in the visual world on the basis of experience.
The seminar will begin at 2:00pm (doors open at 1:30pm) in Room 163, Behavioral Sciences Bldg., on the Keele Campus of York University.
Campus maps can be found at http://www.yorku.ca/web/maps/
For more information please contact John Tsotsos (email@example.com).
This seminar is jointly hosted by the Centre for Vision Research and the Centre for Innovation in Computing at Lassonde.