Program Representation for General Intelligence

Authors
Moshe Looks, Ben Goertzel
Corresponding Author
Moshe Looks
Available Online June 2009.
DOI
https://doi.org/10.2991/agi.2009.32How to use a DOI?
Abstract
Traditional machine learning systems work with relatively flat, uniform data representations, such as feature vectors, time-series, and context-free grammars. However, reality often presents us with data which are best understood in terms of relations, types, hierarchies, and complex functional forms. One possible representational scheme for coping with this sort of complexity is computer programs. This imme- diately raises the question of how programs are to be best represented. We propose an answer in the context of ongoing work towards artificial general intelligence.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
Proceedings of the 2nd Conference on Artificiel General Intelligence (2009)
Part of series
Advances in Intelligent Systems Research
Publication Date
June 2009
ISBN
978-90-78677-24-6
ISSN
1951-6851
DOI
https://doi.org/10.2991/agi.2009.32How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Moshe Looks
AU  - Ben Goertzel
PY  - 2009/06
DA  - 2009/06
TI  - Program Representation for General Intelligence
BT  - Proceedings of the 2nd Conference on Artificiel General Intelligence (2009)
PB  - Atlantis Press
SP  - 146
EP  - 151
SN  - 1951-6851
UR  - https://doi.org/10.2991/agi.2009.32
DO  - https://doi.org/10.2991/agi.2009.32
ID  - Looks2009/06
ER  -