next up previous
Next: Introduction

The New AI:
General & Sound & Relevant for Physics
Technical Report IDSIA-04-03, January 2003 ( Postscript, PDF, arxiv:cs.AI/0302012)
Variant to appear in B. Goertzel and C. Pennachin, eds.:
Artificial General Intelligence (2003, in press, submitted 2002)

Jürgen Schmidhuber -

IDSIA, Galleria 2, 6928 Manno (Lugano), Switzerland


Most traditional artificial intelligence (AI) systems of the past 50 years are either very limited, or based on heuristics, or both. The new millennium, however, has brought substantial progress in the field of theoretically optimal and practically feasible algorithms for prediction, search, inductive inference based on Occam's razor, problem solving, decision making, and reinforcement learning in environments of a very general type. Since inductive inference is at the heart of all inductive sciences, some of the results are relevant not only for AI and computer science but also for physics, provoking nontraditional predictions based on Zuse's thesis of the computer-generated universe.

Related links:
Optimal Ordered Problem Solver
Universal Learning Algorithms
Speed Prior
Optimal universal search
Super Omegas and Generalizations of Algorithmic Information and Probability
In the Beginning was the Code!
Zuse's thesis
Comments on Wolfram's 2002 book
All computable universes
Algorithmic Theories of Everything
Schmidhuber's law

next up previous
Next: Introduction
Juergen Schmidhuber 2003-02-04