首页> 美国政府科技报告 >Retrieval Properties of Neural Networks with Infinitely Many Marked Patterns
【24h】

Retrieval Properties of Neural Networks with Infinitely Many Marked Patterns

机译:具有无穷多标记模式的神经网络的检索性质

获取原文

摘要

An extension of the Hopfield model, where a certain number of 'privileged' (or'marked') patterns enters the Hebb rule with weight 1, while the remaining enter with weight gamma less than 1, was studied. Both sets are infinite. Assuming replica symmetry, the zero temperature capacity minus gamma and overlap minus gamma diagrams are calculated and compared with numerical simulations, when both sets hold the same number of patterns. The transitions from the retrieval to the spin glass phase are found to be first order.

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