首页> 外文期刊>Adaptive Behavior >Associative Learning On A Continuum In Evolved Dynamical Neural Networks
【24h】

Associative Learning On A Continuum In Evolved Dynamical Neural Networks

机译:演化动力神经网络中连续体的联合学习

获取原文
获取原文并翻译 | 示例
           

摘要

This article extends previous work on evolving learning without synaptic plasticity from discrete tasks to continuous tasks. Continuous-time recurrent neural networks without synaptic plasticity are artificially evolved on an associative learning task. The task consists in associating paired stimuli: temperature and food. The temperature to be associated can be either drawn from a discrete set or allowed to range over a continuum of values. We address two questions: Can the learning without synaptic plasticity approach be extended to continuous tasks? And if so, how does learning without synaptic plasticity work in the evolved circuits? Analysis of the most successful circuits to learn discrete stimuli reveal finite state machine (FSM) like internal dynamics. However, when the task is modified to require learning stimuli on the full continuum range, it is not possible to extract a FSM from the internal dynamics. In this case, a continuous state machine is extracted instead.
机译:本文将先前在没有突触可塑性的情况下不断发展的学习的工作从离散任务扩展到了连续任务。没有突触可塑性的连续时间递归神经网络是在联想学习任务上人工进化的。任务在于将成对的刺激相关联:温度和食物。可以从离散集合中提取要关联的温度,也可以让其在连续的值范围内变化。我们解决两个问题:没有突触可塑性方法的学习能否扩展到连续的任务?如果是这样,没有突触可塑性的学习如何在进化的电路中起作用?对学习离散刺激的最成功电路的分析揭示了有限状态机(FSM),如内部动力学。但是,当修改任务以要求在整个连续范围上学习刺激时,就不可能从内部动力学中提取FSM。在这种情况下,将提取连续状态机。

著录项

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