How Gödel‘s Theorem Supports the Possibility of Machine Intelligence

Authors:
Taner Edis
Affiliations:
Department of Physics, Southern University and A & M College, Baton Rouge LA 70813, U.S.A.
Venue:
Minds and Machines
Year:
1998

Citing 6
Cited 0

Reflections on Kurt Go¨del

Reflections on Kurt Go¨del
Algorithmic information theory

Algorithmic information theory
Computational philosophy of science

Computational philosophy of science
Digital mechanics: an informational process based on reversible universal cellular automata

Physica D
On randomized versus deterministic computation

ICALP Selected papers of the twentieth international colloquium on Automata, languages and programming
Matter and Consciousness

Matter and Consciousness

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gödel‘s Theorem is often used in arguments against machineintelligence, suggesting humans are not bound by the rules of any formalsystem. However, Gödelian arguments can be used to support AI,provided we extend our notion of computation to include devicesincorporating random number generators. A complete description scheme can begiven for integer functions, by which nonalgorithmic functions are shown tobe partly random. Not being restricted to algorithms can be accounted for bythe availability of an arbitrary random function. Humans, then, might not berule-bound, but Gödelian arguments also suggest how the relevant sortof nonalgorithmicity may be trivially made available to machines.