Genetic algorithm for artificial neurogenesis

The paper presents a neurogenesis process based on the protein regulation system. The novelty is in applying some genetic algorithm work with neurogenesis, in particular work on genetic operators and work on fitness landscapes. In order to get relevant tests with reduced simulation costs, neurogenesis is applied to a well know problem, the cart-pole system, then results are commented.

[1]  Terry Jones,et al.  Fitness Distance Correlation as a Measure of Problem Difficulty for Genetic Algorithms , 1995, ICGA.

[2]  L. Darrell Whitley,et al.  Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect , 1993, Evolutionary Computation.

[3]  L. Darrell Whitley,et al.  Cellular Encoding Applied to Neurocontrol , 1995, ICGA.

[4]  Nicholas J. Radcliffe,et al.  Equivalence Class Analysis of Genetic Algorithms , 1991, Complex Syst..

[5]  A. P. Wieland,et al.  Evolving neural network controllers for unstable systems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[6]  Jean-Arcady Meyer,et al.  Development, learning and evolution in animats , 1994, Proceedings of PerAc '94. From Perception to Action.

[7]  Philippe Collard,et al.  Artificial neurogenesis: an application to autonomous robotics , 1996, Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence.

[8]  Alexis P. Wieland,et al.  Evolving Controls for Unstable Systems , 1991 .

[9]  Hiroaki Kitano,et al.  Empirical Studies on the Speed of Convergence of Neural Network Training Using Genetic Algorithms , 1990, AAAI.

[10]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[11]  Hugo de Garis,et al.  CAM-BRAIN: The Evolutionary Engineering of a Billion Neuron Artificial Brain by 2001 Which Grows/Evolves at Electronic Speeds Inside a Cellular Automata Machine (CAM) , 1995, Towards Evolvable Hardware.