首页    期刊浏览 2024年11月24日 星期日
登录注册

文章基本信息

  • 标题:Pseudo-Orthogonalization of Memory Patterns for Complex-Valued and Quaternionic Associative Memories
  • 本地全文:下载
  • 作者:Toshifumi Minemoto ; Teijiro Isokawa ; Haruhiko Nishimura
  • 期刊名称:Journal of Artificial Intelligence and Soft Computing Research
  • 电子版ISSN:2083-2567
  • 出版年度:2017
  • 卷号:7
  • 期号:4
  • 页码:257-264
  • DOI:10.1515/jaiscr-2017-0018
  • 出版社:Walter de Gruyter GmbH
  • 摘要:Hebbian learning rule is well known as a memory storing scheme for associative memory models. This scheme is simple and fast, however, its performance gets decreased when memory patterns are not orthogonal each other. Pseudo-orthogonalization is a decorrelating method for memory patterns which uses XNOR masking between the memory patterns and randomly generated patterns. By a combination of this method and Hebbian learning rule, storage capacity of associative memory concerning non-orthogonal patterns is improved without high computational cost. The memory patterns can also be retrieved based on a simulated annealing method by using an external stimulus pattern. By utilizing complex numbers and quaternions, we can extend the pseudo-orthogonalization for complex-valued and quaternionic Hopfield neural networks. In this paper, the extended pseudo-orthogonalization methods for associative memories based on complex numbers and quaternions are examined from the viewpoint of correlations in memory patterns. We show that the method has stable recall performance on highly correlated memory patterns compared to the conventional real-valued method.
  • 关键词:Hopfield neural network ; pseudo; orthogonalization ; complex numbers ; quaternions
国家哲学社会科学文献中心版权所有