Compression Progress: The Algorithmic Principle Behind Curiosity, Creativity, Art, Science, Music, Jokes
1:45-2:30 pm, October 3
I argue that science, art, music, comedy, and many other aspects of intelligent behavior are just by-products of our intrinsic desire to create or discover novel patterns, that is, data compressible in hitherto unknown ways. In other words: non-arbitrary, regular data that is surprising not in the traditional sense of Boltzmann and Shannon but in the sense that it allows for compression progress because its regularity was not yet known. Interestingness is the first derivative of subjective compressibility or simplicity or beauty, that is, the steepness of the learning curve. It is possible to rigorously formalize these concepts and implement them on learning machines, thus building artificial robotic scientists and artists equipped with curiosity and creativity.
Biographies: Jürgen Schmidhuber
Jürgen Schmidhuber is Director of the Swiss Institute for Artificial Intelligence IDSIA (since 1995), Professor of Artificial Intelligence at the University of Lugano, Switzerland (since 2009), Head of Cognitive Robotics 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, USA. 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 on topics such as machine learning, mathematically optimal universal AI, artificial curiosity and creativity, artificial recurrent neural networks, adaptive robotics, complexity theory, digital physics, theory of beauty, and the fine arts.
