Molecular self-organisation in a developmental model for the evolution of large-scale artificial neural networks

H. Bolouri, R.G. Adams, S. George, A.G. Rust

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Downloads (Pure)

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the 1998 International Conference on Neural Information Processing and Intelligent Information Systems (ICONIP'98)
Pages797-800
Volume2
Publication statusPublished - 1998

Fingerprint

Dive into the research topics of 'Molecular self-organisation in a developmental model for the evolution of large-scale artificial neural networks'. Together they form a unique fingerprint.

Cite this