The New AI: General & Sound & Relevant for Physics
Abstract
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.
Cite
@article{arxiv.cs/0302012,
title = {The New AI: General & Sound & Relevant for Physics},
author = {Juergen Schmidhuber},
journal= {arXiv preprint arXiv:cs/0302012},
year = {2007}
}
Comments
23 pages, updated refs, added Goedel machine overview, corrected computing history timeline. To appear in B. Goertzel and C. Pennachin, eds.: Artificial General Intelligence