Computational Principles for Deep Neuronal Architectures
Haim Sompolinsky
2015 Invited Talk
Abstract
Recent progress in machine applications of deep neural networks have highlighted the need for a theoretical understanding of the capacity and limitations of these architectures. I will review our understanding of sensory processing in such architectures in the context of the hierarchies of processing stages observed in many brain systems. I will also address the possible roles of recurrent and top - down connections, which are prominent features of brain information processing circuits.
Speaker
Haim Sompolinsky
Chat is not available.
Successful Page Load