作者: Tuze Kuyucu , Martin Trefzer , Julian F. Miller , Andy Tyrrell
DOI: 10.1109/ALIFE.2009.4937701
关键词:
摘要: The design of a new biologically inspired artificial developmental system is described in this paper. In general, systems converge slower and are more computationally expensive than direct evolution. However, the performance trends development indicate that full benefit will arise with larger complex problems exhibit some sort regularity their structure: thus, aim to evolve electronic through modularity allowed by development. hope proposed adaptivity fault tolerance future. cell signalling Gene Regulatory Networks present biological organisms modelled our system, tailored for tackling real world on hardware. For first time, Network successfully shown develop complete circuit structure desired digital without help another mechanism or any problem specific structuring. Experiments presented show modular behaviour as well its ability solve non-modular problems.