Aude Oliva

With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Using a combination of neuro-imaging techniques of the human brain, and computer science methods, the talk will show how meaningful information emerge in the human brain, and within deep learning architectures, and how CNN architectures can benefit from neuroscience.