论文信息 - From the Chromosome to the Neural Network

From the Chromosome to the Neural Network

A proposal for a model of morphogenesis process taking inspiration from biology is presented in this paper. This process uses a chromosome as a production system to create an artificial neural network. It starts with a single cell containing the chromosome. Cells can divide and establish connections among them. Both structure and weights of the neural network are defined by the morphogenesis process. An application to a neural network driving an autonomous mobile robot is presented which exhibits encouraging first results.

Olivier Michel | Joëlle Biondi | O. Michel | Joëlle Biondi

[1] V. Braitenberg. Vehicles, Experiments in Synthetic Psychology , 1984 .

[2] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[3] Teuvo Kohonen,et al. Self-organization and associative memory: 3rd edition , 1989 .

[4] J. David Schaffer,et al. Proceedings of the third international conference on Genetic algorithms , 1989 .

[5] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[6] Peter M. Todd,et al. Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[7] Brad Fullmer and Risto Miikkulainen. Using Marker-Based Genetic Encoding Of Neural Networks To Evolve Finite-State Behaviour , 1991 .

[8] SAGAInman HarveyCSRP. Species Adaptation Genetic Algorithms: A Basis for a Continuing SAGA , 1992 .

[9] P Bourgine,et al. Towards a Practice of Autonomous Systems , 1992 .

[10] Inman Harvey,et al. Explorations in Evolutionary Robotics , 1993, Adapt. Behav..

[11] Francesco Mondada,et al. Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[12] Frédéric Gruau,et al. The cellular development of neural networks: the interaction of learning and evolution , 1993 .