Building Complex Systems Using Developmental Process: An Engineering Approach

作者: Hiroaki Kitano

DOI: 10.1007/BFB0057623

关键词: Human–computer interactionEvolutionary computationScale (chemistry)Artificial lifeNetwork topologyArtificial neural networkBiological modelingAdaptive systemComplex systemComputer scienceArtificial intelligenceProcess (engineering)

摘要: One of the central challenges evolutionary computing and artificial life research is to establish a methodology for building very large complex system which has functional structures. Although it increasingly recognized that use developmental process promising approach, none existing method can create structures involving scale repetitive subunits characterize biological systems, such as brain, animal body, memory chips. In this paper, we present powerful developing based on grammar-based approach. The introduction novel meta-node associated operations essential feature method. We demonstrate strength by actually network topologies identical human receptive fields skin touch stimuli cerebeller cortex.

参考文章(7)
Aristid Lindenmayer, Mathematical models for cellular interactions in development I. Filaments with one-sided inputs Journal of Theoretical Biology. ,vol. 18, pp. 280- 299 ,(1968) , 10.1016/0022-5193(68)90079-9
Frederic Gruau, Darrell Whitley, None, Adding learning to the cellular development of neural networks: Evolution and the baldwin effect Evolutionary Computation. ,vol. 1, pp. 213- 233 ,(1993) , 10.1162/EVCO.1993.1.3.213
Aristid Lindenmayer, Developmental systems without cellular interactions, their languages and grammars Journal of Theoretical Biology. ,vol. 30, pp. 455- 484 ,(1971) , 10.1016/0022-5193(71)90002-6
Karl Sims, Evolving 3d morphology and behavior by competition Artificial Life. ,vol. 1, pp. 353- 372 ,(1994) , 10.1162/ARTL.1994.1.353