Adaptive Behavior through a Darwinist Machine

In this paper we propose a mechanism based on Darwinist principles applied on-line that provides organisms with the capability of adapting through the use of their interaction with their surroundings in order to improve the level of satisfaction obtained. The mechanism involves a two level concurrent operation of evolutionary processes. The processing carried out in the first, or unconscious level, leads to a current, or conscious model of the world and the organism, which is employed for evaluating candidate strategies, using as fitness the predicted motivation satisfaction.

[1]  Gerhard Weiß,et al.  Neural networks and evolutionary computation. Part II: hybrid approaches in the neurosciences , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[2]  M. Conrad.  Evolutionary learning circuits. , 1974, Journal of theoretical biology.

[3]  G. Edelman.  Neural Darwinism: The Theory Of Neuronal Group Selection , 1989 .

[4]  J. Changeux,et al.  Selective stabilisation of developing synapses as a mechanism for the specification of neuronal networks , 1976, Nature.

[5]  Peter Nordin,et al.  Evolution of a world model for a miniature robot using genetic programming , 1998, Robotics Auton. Syst..

[6]  Jean-Pierre Changeux,et al.  Learning by Selection , 1984 .

[7]  H. Terrace,et al.  The Biology of Learning , 1984, Dahlem Workshop Reports.