Search

Workshop

Optimal AI - neural network ReNNaissance - theory of fun

  • Jürgen Schmidhuber (Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Lugano, Switzerland)
E1 05 (Leibniz-Saal)

Abstract

Our fast, deep/recurrent neural networks have many biologically plausible, non-linear processing stages. They won eight recent international pattern recognition competitions, and set records in many vision benchmarks, contributing to the ongoing second Neural Network ReNNaissance. We are starting to use them 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 (possibly neural) predictor or compressor or model of the growing data history as the agent is interacting with its environment, and
  2. a (possibly neural) 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 & humor. 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.

 

Overview pages with papers on the touched subjects:

<link http: www.idsia.ch creativity.html external>www.idsia.ch/~juergen/creativity.html

<link http: www.idsia.ch interest.html external>www.idsia.ch/~juergen/interest.html

<link http: www.idsia.ch vision.html external>www.idsia.ch/~juergen/vision.html

<link http: www.idsia.ch handwriting.html external>www.idsia.ch/~juergen/handwriting.html

<link http: www.idsia.ch rnnbook.html external>www.idsia.ch/~juergen/rnnbook.html

<link http: www.idsia.ch rl.html external>www.idsia.ch/~juergen/rl.html

<link http: www.idsia.ch evolution.html external>www.idsia.ch/~juergen/evolution.html

<link http: www.idsia.ch ica.html external>www.idsia.ch/~juergen/ica.html

<link http: www.idsia.ch unilearn.html external>www.idsia.ch/~juergen/unilearn.html

<link http: www.idsia.ch goedelmachine.html external>www.idsia.ch/~juergen/goedelmachine.html

<link http: www.idsia.ch videos.html external>Some videos on this: www.idsia.ch/~juergen/videos.html

Links

Antje Vandenberg

Max Planck Institute for Mathematics in the Sciences Contact via Mail

Nihat Ay

Max Planck Institute for Mathematics in the Sciences

Ralf Der

Max Planck Institute for Mathematics in the Sciences

Keyan Ghazi-Zahedi

Max Planck Institute for Mathematics in the Sciences

Georg Martius

Max Planck Institute for Mathematics in the Sciences