首页> 外文期刊>Network >Stability criteria for the contextual emergence of macrostates in neural networks
【24h】

Stability criteria for the contextual emergence of macrostates in neural networks

机译:神经网络中宏状态上下文出现的稳定性标准

获取原文
获取原文并翻译 | 示例
           

摘要

More than thirty years ago, Amari and colleagues proposed a statistical framework for identifying structurally stable macrostates of neural networks from observations of their microstates. We compare their stochastic stability criterion with a deterministic stability criterion based on the ergodic theory of dynamical systems, recently proposed for the scheme of contextual emergence and applied to particular inter-level relations in neuroscience. Stochastic and deterministic stability criteria for macrostates rely on macro-level contexts, which make them sensitive to differences between different macro-levels.
机译:三十多年前,Amari及其同事提出了一个统计框架,用于从对微网络状态的观察中识别出结构稳定的神经网络宏观状态。我们将它们的随机稳定性标准与基于动力学系统遍历理论的确定性稳定性标准进行比较,该稳定性标准最近针对情境出现方案提出,并应用于神经科学中的特定层间关系。宏观状态的随机性和确定性稳定性标准依赖于宏观级别的上下文,这使它们对不同宏观级别之间的差异敏感。

著录项

  • 来源
    《Network》 |2009年第3期|178-196|共19页
  • 作者单位

    School of Psychology and Clinical Language Sciences, University of Reading, UK University of Reading, Department of Clinical Language Sciences, Whiteknights, PO Box 217, Reading, RG6 6AH United Kingdom;

    Department of Informatics, University of Sussex, UK;

    Institute for Frontier Areas of Psychology and Mental Health, Freiburg, Germany;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    network models;

    机译:网络模型;

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