Hebbian Constraint on the Resolution of the Homunculus Fallacy Leads to a Network that Searches for Hidden Cause-Effect Relationships

DOI

10.2991/agi.2009.36How to use a DOI?

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 Subspace 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.

Copyright

© 2009, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - András Lorincz
PY  - 2009/06
DA  - 2009/06
TI  - Hebbian Constraint on the Resolution of the Homunculus Fallacy Leads to a Network that Searches for Hidden Cause-Effect Relationships
BT  - Proceedings of the 2nd Conference on Artificial General Intelligence (2009)
PB  - Atlantis Press
SP  - 170
EP  - 175
SN  - 1951-6851
UR  - https://doi.org/10.2991/agi.2009.36
DO  - 10.2991/agi.2009.36
ID  - Lorincz2009/06
ER  -