Date: Wednesday, 22.06.22 17:00 CET
Signup: If you would like to attend the talks please register here to get a Zoom link.
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 field circuits 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.
Bio:
Dr. Serre is a Professor in Cognitive Linguistic & Psychological Sciences and in Computer Science, and an affiliate of the Carney Institute for Brain Science at Brown University. He is the Faculty Director of the Center for Computation & Visualization and Associate Director of the Center for Computational Brain Science. He also holds an International Chair in AI within the ANR-3IA Artificial and Natural Intelligence Toulouse Institute (France). He received a Ph.D. in Neuroscience from MIT in 2006 and an MSc in EECS from Télécom Bretagne (France) in 2000.
His research seeks to understand the neural computations supporting visual perception. His group works at the intersection between biological and artificial vision. Dr. Serre serves routinely as an area chair for leading computational neuroscience, machine learning and computer vision conferences including AAAI, CVPR, ICLR, ICML and NeurIPS. He is also Deputy Editor at PLOS Computational Biology and an Editorial Board Member at eLife. He has received multiple awards: one of his papers received the PAMI Helmholtz Prize for significant impact on computer vision research and he was the recipient of an NSF Early Career Award as well as DARPA’s Young Faculty Award and Director’s Award, among others.
Lab link:
