Differences between kolmogorov complexity and solomonoff probability: consequences for AGI

Authors:
Alexey Potapov;Andrew Svitenkov;Yurii Vinogradov
Affiliations:
AIDEUS, Russia;National Research University of Information Technology Mechanics and Optics, Russia;National Research University of Information Technology Mechanics and Optics, Russia
Venue:
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
Year:
2012

Citing 5
Cited 0

The discovery of algorithmic probability

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability

Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
MDL convergence speed for Bernoulli sequences

Statistics and Computing
Delusion, survival, and intelligent agents

AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Compression and intelligence: social environments and communication

AGI'11 Proceedings of the 4th international conference on Artificial general intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Kolmogorov complexity and algorithmic probability are compared in the context of the universal algorithmic intelligence. Accuracy of time series prediction based on single best model and on averaging over multiple models is estimated. Connection between inductive behavior and multi-model prediction is established. Uncertainty as a heuristic for reducing the number of used models without losses of universality is discussed. The conclusion is made that plurality of models is the essential feature of artificial general intelligence, and this feature should not be removed without necessity.