Monostable Controllers for Adaptive Behaviour

详细信息    查看全文

• 作者：Christopher L. Buckley ; Peter Fine ; Seth Bullock ; Ezequiel Di Paolo
• 关键词：Global stability ; echo state networks ; evolvability
• 刊名：Lecture Notes in Computer Science
• 出版年：2008
• 出版时间：2008
• 年：2008
• 卷：5040
• 期：1
• 页码：103-112
• 全文大小：494.4 KB

文摘

Recent artificial neural networks for machine learning have exploited transient dynamics around globally stable attractors, inspired by the properties of cortical microcolumns. Here we explore whether similarly constrained neural network controllers can be exploited for embodied, situated adaptive behaviour. We demonstrate that it is possible to evolve globally stable neurocontrollers containing a single basin of attraction, which nevertheless sustain multiple modes of behaviour. This is achieved by exploiting interaction between environmental input and transient dynamics. We present results that suggest that this globally stable regime may constitute an evolvable and dynamically rich subset of recurrent neural network configurations, especially in larger networks. We discuss the issue of scalability and the possibility that there may be alternative adaptive behaviour tasks that are more ‘attractor hungry’.