What we might look for in an AGI benchmark
Available Online June 2010.
- https://doi.org/10.2991/agi.2010.5How to use a DOI?
- A benchmark in the Â¯eld of ArtiÂ¯cial General Intelligence (AGI) would allow evaluation and comparison of the many computational intelligence algorithms that have been developed. In this paper I propose that an ideal benchmark would possess seven key characteristics: Â¯tness, breadth, specificity, low cost, simplicity,range, and task focus.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Brandon Rohrer PY - 2010/06 DA - 2010/06 TI - What we might look for in an AGI benchmark BT - 3d Conference on Artificial General Intelligence (AGI-2010) PB - Atlantis Press SP - 21 EP - 26 SN - 1951-6851 UR - https://doi.org/10.2991/agi.2010.5 DO - https://doi.org/10.2991/agi.2010.5 ID - Rohrer2010/06 ER -