Feedforward and Feedback Processes in Visual Recognition

11 June 2020, 13.00 - 14.00, online

Thomas Serre (Cognitive, Linguistic & Psychological Sciences Department, Carney Institute for Brain Science, Brown University)
Hosted by the Generalisation in Mind and Machine research group

Join via Zoom: us02web.zoom.us/j/88556082000?pwd=VldkYn...Z1M4aUJGWGJBTFlvZz09
Meeting ID: 885 5608 2000
Password: 694077

Abstract | Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching – and sometimes even surpassing – human accuracy on a variety of visual recognition tasks. In this talk, however, I will show that these neural networks and their recent extensions exhibit a limited ability to solve seemingly simple visual reasoning problems involving incremental grouping, similarity, and spatial relation judgments. Our group has developed a recurrent network model of classical and extra-classical receptive fields that is constrained by the anatomy and physiology of the visual cortex. The model was shown to account for diverse visual illusions providing computational evidence for a novel canonical circuit that is shared across visual modalities. I will show that this computational neuroscience model can be turned into a modern end-to-end trainable deep recurrent network architecture that addresses some of the shortcomings exhibited by state-of-the-art feedforward networks for solving complex visual reasoning tasks. This suggests that neuroscience may contribute powerful new ideas and approaches to computer science and artificial intelligence.