Hierarchical Cooperative CoEvolution Facilitates the Redesign of Agent-Based Systems
The current work addresses the problem of redesigning brain-inspired artificial cognitive systems in order to gradually enrich them with advanced cognitive skills. In the proposed approach, properly formulated neural agents are employed to represent brain areas. A cooperative coevolutionary method, with the inherent ability to co-adapt substructures, supports the design of agents. Interestingly enough, the same method provides a consistent mechanism to reconfigure (if necessary) the structure of agents, facilitating follow-up modelling efforts. In the present work we demonstrate partial redesign of a brain-inspired cognitive system, in order to furnish it with learning abilities. The implemented model is successfully embedded in a simulated robotic platform which supports environmental interaction, exhibiting the ability of the improved cognitive system to adopt, in real-time, two different operating strategies.
KeywordsVentral Tegmental Area Response Strategy Posterior Parietal Cortex Excitatory Neuron Coevolutionary Process
Unable to display preview. Download preview PDF.
- 1.Krichmar, J., Edelman, G.: Brain-based devices: Intelligent systems based on principles of the nervous system. In: Proc. 2003 IEEE/RSJ Int. Conference on Intelligent Robots and Systems, pp. 940–945 (2003)Google Scholar
- 3.Maniadakis, M., Trahanias, P.: Modelling brain emergent behaviors through coevolution of neural agents. Neural Networks Journal (accepted for publication, 2006)Google Scholar
- 4.Maniadakis, M., Trahanias, P.: Distributed brain modelling by means of hierarchical collaborative coevolution. In: Proc. IEEE Congress on Evolutionary Computation (CEC), pp. 2699–2706 (2005)Google Scholar
- 5.Maniadakis, M., Trahanias, P.: Design and integration of partial brain models using hierarchical cooperative coevolution. In: Proc. International Conference on Cognitive Modelling, ICCM (2006)Google Scholar
- 8.Blynel, J., Floreano, D.: Levels of dynamics and adaptive behaviour in evolutionary neural controllers. In: Proc. of the Seventh International Conference on Simulation of Adaptive Behavior (SAB), pp. 272–281 (2002)Google Scholar
- 12.Kandel, E.R., Schwartz, J., Jessell, T.M.: Principles of Neural Science. McGraw Hill, New York (2000)Google Scholar