Spatially Constrained Networks and the Evolution of Modular Control Systems
Spatially Constrained Networks and the Evolution of Modular Control Systems
复制标题
空间约束网络和模块化控制系统的演变
DOI：
--
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
Andrew O. Philippides
中科院分区：
文献类型：
--
作者：
Peter Fine;E. Paolo;Andrew O. Philippides
本文研究了空间嵌入式神经网络模型与模块化之间的关系。假设空间约束导致更大的机会进化模块化结构。首先，在最小模块化任务/控制器场景中测试了空间嵌入式神经网络模型。网络连接的非空间形式然后，我们应用这种见解来检查不同程度的空间约束对在更复杂，我们的结论是，偏向模块化也许并不总是一个理想的属性控制系统范例拥有。
This paper investigates the relationship between spatially embedded neural network models and modularity It is hypothesised that spatial constraints lead to a greater chance of evolving modular structures Firstly, this is tested in a minimally modular task/controller scenario Spatial networks were shown to possess the ability to generate modular controllers which were not found in standard, non-spatial forms of network connectivity We then apply this insight to examine the effect of varying degrees of spatial constraint on the modularity of a controller operating in a more complex, situated and embodied simulated environment We conclude that a bias towards modularity is perhaps not always a desirable property for a control system paradigm to possess.