Jürgen Schmidhuber

Dalle Molle Institute for Artificial Intelligence and Università della Svizzera italiana, Lugano, Switzerland

Compression Progress: The Algorithmic Principle Behind Curiosity and Creativity

Summary

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.

Papers on this (1990-2009): http://www.idsia.ch/~juergen/interest.html

Resume and more information

Homepage: http://www.idsia.ch/~juergen/

Theory of subjective beauty: http://www.idsia.ch/~juergen/beauty.html

This talk is taken from the Singularity Summit 2009 recordings at vimeo.com with permission from the lecturer and producer.