Events Calendar

Neural Network ReNNaissance: Jürgen Schmidhuber (Swiss AI Lab IDSIA)

Speaker: Jürgen Schmidhuber, Swiss AI Lab IDSIA

Talk Title: Neural Network ReNNaissance

Series: CS Colloquium

Abstract: Our fast, deep / recurrent neural networks won eight recent international pattern recognition competitions, and are the first machine learning methods to achieve human-competitive or superhuman performance on well-known benchmarks. We also can evolve big NN controllers without any supervision, using "compressed" encodings of NN weight matrices represented indirectly as a set of Fourier-type coefficients. Recently, the largest, evolved, vision-based NN controller to date, with over 1 million weights, learned to drive a car around a track using raw video images from the driver's perspective in the TORCS driving game. We are starting to use such methods in active, unsupervised, curious, creative systems of a type we introduced in 1990. They learn to sequentially shift attention towards informative inputs, not only solving externally posed tasks, but also their own self-generated tasks designed to improve their understanding of the world according to our Formal Theory of Fun and Creativity, which requires two interacting modules: (1) an adaptive predictor or compressor or model of the growing data history as the agent is interacting with its environment, and (2) a reinforcement learner. The learning progress of (1) is the FUN or intrinsic reward of (2). That is, (2) is motivated to invent skills leading to interesting or surprising novel patterns that (1) does not yet know but can easily learn (until they become boring). We discuss how this simple principle explains science & art & music & humour. Time permitting, I'll also briefly discuss the recent theoretically optimal universal problem solvers pioneered in our lab, such as Gödel machines and the asymptotically fastest algorithm for all well-defined problems.

Biography: Prof. Jürgen Schmidhuber is with the Swiss AI Lab IDSIA & USI & SUPSI (ex-TUM CogBotLab &CU). Since age 15 or so his main scientific ambition has been to build an optimal scientist, then retire. This is driving his research on self-improving Artificial Intelligence. His team won many international competitions and awards, and pioneered the field of mathematically rigorous universal AI and optimal universal problem solvers. He also generalized the many-worlds theory of physics to a theory of all constructively computable universes - an algorithmic theory of everything. His formal theory of creativity & curiosity & fun (1990-2010) explains art, science, music, and humor.

Host: Stefan Schaal

Location: Ronald Tutor Hall of Engineering (RTH) - 422

Audiences: Everyone Is Invited

Contact: Assistant to CS chair