Vidéo
How to Obtain and Run Light and Efficient Deep Learning Networks
Fast growth of the computation cost associated with training and testing of deep neural networks (DNNs) inspired various acceleration techniques. Reducing topological complexity and simplifying data representation of neural networks are two approaches that popularly…
Publication
The case for experiment-oriented computing
Publication
RefiNym: using names to refine types
Publication
Deep learning type inference
Vidéo
Reinforcement Learning: Bringing Together Computation, Behavior and Neural Coding
Reinforcement learning carries subtly different meanings in machine learning, cognitive science and neuroscience. In this talk, I will try to clarify in which ways the concepts overlap and in which ways they differ. I will…