We argue that molecular self-organisation during embryonic development allows evolution to perform highly nonlinear combinatorial optimisation. A structured approach to architectural optimisation of large-scale Artificial Neural Networks using this principle is presented. We also present simulation results demonstrating the evolution of an edge detecting retina using the proposed methodology.
|Title of host publication||Proceedings of the 1998 International Conference on Neural Information Processing and Intelligent Information Systems (ICONIP'98)|
|Publication status||Published - 1998|