Program Representation for General Intelligence
Moshe Looks, Ben Goertzel
Available Online June 2009.
- https://doi.org/10.2991/agi.2009.32How to use a DOI?
- 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.
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 -