首页    期刊浏览 2024年11月15日 星期五
登录注册

文章基本信息

  • 标题:Complexity Constraints and Error Tolerance in Learning Processes on Small Graphs
  • 本地全文:下载
  • 作者:H. Atmanspacher ; T. Filk ; R. Finke
  • 期刊名称:The Open Cybernetics & Systemics Journal
  • 电子版ISSN:1874-110X
  • 出版年度:2010
  • 卷号:4
  • 期号:1
  • 页码:6-13
  • DOI:10.2174/1874110X01004010006
  • 出版社:Bentham Science Publishers Ltd
  • 摘要:

    Continuing previous studies, we present further results about the behavior of small abstract networks during supervised learning. In particular, we show that constraints on the complexity that a network is permitted to assume during learning reduces its learning success in ways that depend on the nature of the applied limitation. Moreover, we show that relaxing the criterion due to which changes of the network structure are accepted during learning leads to a dramatic improvement of the learning performance. The non-monotonicity of network complexity during learning, which remains unchanged in both scenarios, is related to a similar feature in -machine complexity.

国家哲学社会科学文献中心版权所有