Towards a theory of AI completeness

Dafna Shahaf*, Eyal Amir

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Scopus citations


In this paper we present a novel classification of computational problems. Motivated by a theoretical investigation of Artificial Intelligence (AI), we present (1) a complexity model for computational problems that includes a human in the process, and (2) a classification of prototypical problems treated in the AI literature. The contribution of this paper is useful for automatically distinguishing between human and computer users. Also, this work serves as a formal basis for investigation of problems that researchers treat as hard AI problems. Most importantly, this work allows progress in AI as a field to be more measurable, instead of measurable with respect to problem-specific quantities.

Original languageAmerican English
Title of host publicationLogical Formalizations of Commonsense Reasoning - Papers from the 2007 AAAI Spring Symposium, Technical Report
Number of pages6
StatePublished - 2007
Externally publishedYes
Event2007 AAAI Spring Symposium - Stanford, CA, United States
Duration: 26 Mar 200728 Mar 2007

Publication series

NameAAAI Spring Symposium - Technical Report


Conference2007 AAAI Spring Symposium
Country/TerritoryUnited States
CityStanford, CA


Dive into the research topics of 'Towards a theory of AI completeness'. Together they form a unique fingerprint.

Cite this