This is part 2 of my conversation with Brad (listen to part 1 here). We discuss how Moore’s law is on its last legs, and his ideas for how neuroscience - in particular neural algorithms - may help computing continue to scale in a post-Moore’s law world. We also discuss neuromporphics in general, and more.
Jay's homepage at Stanford.Implementing mathematical reasoning in machines:The video lecture.The paper.Parallel Distributed Processing by Rumelhart and McClelland.Complimentary Learning Systems Theory and Its Recent Update.Episode...
Galit and I discuss the independent roles of prediction and explanation in scientific models, their history and eventual separation in the philosophy of science,...
Jim and I discuss his reverse engineering approach to visual intelligence, using deep models optimized to perform object recognition tasks. We talk about the...