Monostable controllers for adaptive behavior

C. L. Buckley, Peter Fine, Seth Bullock, Ezequiel Di Paolo

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

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'.
Original languageUndefined/Unknown
Title of host publicationFrom Animals to Animats 10: Proceedings of the Tenth International Conference on Simulation of Adaptive Behavior (SAB 2008)
EditorsM. Asada, J. C. T. Hallam, J.-A. Meyer, J. Tani
PublisherSpringer
Pages103-112
Number of pages10
Publication statusPublished - 2008

Keywords

  • Global stability, echo state networks, evolvability

Cite this