J�rgen Schmidhuber

Juergen Schmidhuber

Jürgen Schmidhuber wants to build an optimal scientist, then retire. He is Director of the Swiss Artificial Intelligence Lab IDSIA (since 1995), Professor of Artificial Intelligence at the University of Lugano, Switzerland (since 2009), Head of the CogBotLab at TU Munich,Germany (since 2004, as Professor Extraordinarius until 2009), and Professor SUPSI, Switzerland (since 2003). He obtained his doctoral degree in computer science from TUM in 1991 and his Habilitation degree in 1993, after a postdoctoral stay at the University of Colorado at Boulder. He helped to transform IDSIA into one of the world's top ten AI labs (the smallest!), according to the ranking of Business Week Magazine. He is a member of the European Academy of Sciences and Arts, and has published more than 200 peer-reviewed scientific papers (some won best paper awards) on topics such as machine learning, mathematically optimal universal AI, artificial curiosity and creativity, artificial recurrent neural networks (which won several recent handwriting recognition contests), adaptive robotics, algorithmic information and complexity theory, digital physics, theory of beauty, and the fine arts.

Formal Theory of Fun & Creativity

To build a creative agent that never stops generating non-trivial & novel & surprising data, we need two learning 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 general reinforcement learner. The LEARNING PROGRESS of (1) is the FUN or intrinsic reward of (2). That is, (2) is motivated to invent interesting things that (1) does not yet know but can easily learn. To maximize expected reward, in the absence of external reward (2) will create more and more complex behaviors that yield temporarily surprising (but eventually boring) patterns that make (1) quickly improve. We discuss how this principle explains science & art & music & humor, and how to scale up previous toy implementations of the theory since 1991, using recent powerful methods for (1) prediction and (2) reinforcement learning.


Made with goita - OpenSource CMS