首页> 外文会议>International conference on the simulation and synthesis of living systems >Analysis of a Dynamical Recurrent Neural Network Evolved for Two Qualitatively Different Tasks: Walking and Chemotaxis
【24h】

Analysis of a Dynamical Recurrent Neural Network Evolved for Two Qualitatively Different Tasks: Walking and Chemotaxis

机译:动态递归神经网络进化为两个性质不同的任务:行走和趋化性的分析。

获取原文

摘要

Living organisms perform a broad range of different behaviours during their lifetime. It is important that these be coordinated such as to perform the appropriate one at the right time. This paper extends previous work on evolving dynamical recurrent neural networks by synthesizing a single circuit that performs two qualitatively different behaviours: orientation to sensory stimuli and legged locomotion. We demonstrate that small fully interconnected networks can solve these two tasks without providing a priori structural modules, explicit neural learning mechanisms, or an external signal for when to switch between them. Dynamical systems analysis of the best-adapted circuit explains the agent's ability to switch between the two behaviours from the interactions of the circuit's neural dynamics, its body and environment.
机译:生命有机体在其一生中会执行各种不同的行为。重要的是要进行协调,以便在正确的时间执行适当的操作。本文通过合成执行两种在性质上不同的行为:对感觉刺激的定向和有腿运动的行为的单个电路,扩展了关于动态循环神经网络的先前工作。我们证明了小型的完全互连的网络可以解决这两项任务,而无需提供先验的结构模块,明确的神经学习机制或何时在它们之间进行切换的外部信号。最佳适应电路的动力学系统分析说明了代理在电路的神经动力学,其主体和环境之间的相互作用中在两种行为之间进行切换的能力。

著录项

  • 来源
  • 会议地点 Winchester(GB)
  • 作者单位

    Centre for Systems Biology University of Birmingham Edgbaston Birmingham B15 2TT UK Centre for Computational Neuroscience and Robotics University of Sussex Brighton BN1 9QH UK;

    Centre for Computational Neuroscience and Robotics University of Sussex Brighton BN1 9QH UK Natural Motion Ltd Oxford OX1 2ET UK;

  • 会议组织
  • 原文格式 PDF
  • 正文语种
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号