The Piagetian Autonomous Modeler - An Artificial Intelligence architecture for a system that constructs an internal representation of a real or simulated environment based on its interaction with the environment. The novel aspects of the modeler are: (1) how it spreads activation; (2) its use of schemes (structural and behavioral) to connect the representational units (monads); (3) its use of multi-strategy inference to extend the internal model; (4) its use of a consolidation component to provide automaticity and forgetting; and (5) its evolution of successful behaviors through equilibration (using genetic adaptation).

The system is called Piagetian because it employs the notion of Monads (fundamental representational units), Schemes (patterns of structure and behavior), Assimilation (incorporating external elements) and Accommodation (modifying internal structures in accordance with environmental feedback) which are essential to the theories of Human Cognitive Development espoused by Piaget.

.

You can find a concise description of the system here:

http://www.scribd.com/doc/50398031/PAM-Concise-v7

or here:    http://www.abdn.ac.uk/~csc245/Miller.pdf

.

Artificial Intelligence and Simulation of Behavior 2011 Conference talk

April 5, 2011 at the University of York (United Kingdom):

http://www.scribd.com/doc/51981938/PAM-Talk-AISB-11

.

Kindly send comments to:  PiagetModeler@Hotmail.com

Also on Facebook (search by the e-mail above).

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Tue 04 Oct 2011

An improved architecture for the modeler has been created which satisfies the augmented system requirements (soon to be published). 

.

Sun 10 Apr 2011

New ideas ~ Looking for a good sub-architecture for attention management: i.e., model switching between prospection (the forward model), retrospection (the episode model), and the perception-response (the current model). 

Suggestions welcome!!     See    http://attentionarchitectures.tumblr.com/