ENS, Jaurès, 29 rue d'Ulm, 75005 Paris
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 recent extensions) exhibit a limited ability to solve seemingly simple visual reasoning problems. Our group has developed a computational neuroscience model of the feedback circuitry found in the visual cortex. The model was constrained by the anatomy and physiology of the visual cortex and 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 visual reasoning. This suggests that neuroscience may contribute powerful new ideas and approaches to computer science and artificial intelligence.
This colloquium is organized around data sciences in a broad sense, with the goal of bringing together researchers with diverse backgrounds (including mathematics, computer science, physics, chemistry and neuroscience) but a common interest in dealing with complex, large scale, or high dimensional data. More information can be found on the web page of the seminar: https://data-ens.github.io/seminar/
These seminars are being made possible through the support of the CFM-ENS Chair "Modèles et Sciences des Données”.