Hebbian Constraint on the Resolution of the Homunculus Fallacy

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

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.