Towards heuristic algorithmic memory

Date

2011

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

BUIR Usage Stats
2
views
51
downloads

Citation Stats

Attention Stats

Series

Abstract

We propose a long-term memory design for artificial general intelligence based on Solomonoff's incremental machine learning methods. We introduce four synergistic update algorithms that use a Stochastic Context-Free Grammar as a guiding probability distribution of programs. The update algorithms accomplish adjusting production probabilities, re-using previous solutions, learning programming idioms and discovery of frequent subprograms. A controlled experiment with a long training sequence shows that our incremental learning approach is effective. © 2011 Springer-Verlag Berlin Heidelberg.

Source Title

Artificial General Intelligence

Publisher

Springer, Berlin, Heidelberg

Course

Other identifiers

Book Title

Degree Discipline

Degree Level

Degree Name

Citation

Language

English