Deep Learning in Action | How to learn an algorithm

Deep Learning in Action | A talk by Juergen Schmidhuber, PhD at the Deep Learning in Action talk series in October 2015. He is professor in computer science at the Dalle Molle Institute for Artificial Intelligence Research, part of the University of Applied Sciences and Arts of Southern Switzerland. Juergen Schmidhuber, PhD | I review 3 decades of our research on both gradient based and more general problem solvers that search the space of algorithms running on general purpose computers with internal memory. Architectures include traditional computers, Turing machines, recurrent neural networks, fast weight networks, stack machines, and others. Some of our algorithm searchers are based on algorithmic information theory and are optimal in asymptotic or other senses. Most can learn to direct internal and external spotlights of attention. Some of…


Link to Full Article: Deep Learning in Action | How to learn an algorithm