Hebbian constraint on the resolution of the homunculus fallacy leads to a network that searches for hidden cause-effect relationships

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We elaborate on a potential resolution of the homunculus fallacy that leads to a minimal and simple auto-associative recurrent 'reconstruction network.' architecture. We insist on Hebbian constraint at each learning step executed in this network. We find that the hidden internal model enables searches for cause-effect relationships in, the form of autoregressive models under certain conditions. We discuss the connection between hidden causes and Independent Subšpace Analysis. We speculate that conscious experience is the result of competition between various learned hidden models for spatio-temporal reconstruction of ongoing effects of the detected hidden causes.

Original languageEnglish
Title of host publicationProceedings of the 2nd Conference on Artificial General Intelligence, AGI 2009
Pages126-131
Number of pages6
Publication statusPublished - Dec 1 2009
Event2nd Conference on Artificial General Intelligence, AGI 2009 - Arlington, VA, United States
Duration: Mar 6 2009Mar 9 2009

Publication series

NameProceedings of the 2nd Conference on Artificial General Intelligence, AGI 2009

Other

Other2nd Conference on Artificial General Intelligence, AGI 2009
CountryUnited States
CityArlington, VA
Period3/6/093/9/09

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics

Cite this

Lörincz, A. (2009). Hebbian constraint on the resolution of the homunculus fallacy leads to a network that searches for hidden cause-effect relationships. In Proceedings of the 2nd Conference on Artificial General Intelligence, AGI 2009 (pp. 126-131). (Proceedings of the 2nd Conference on Artificial General Intelligence, AGI 2009).