首页> 外文期刊>Journal of Statistical Physics >On a Model of Associative Memory with Huge Storage Capacity
【24h】

On a Model of Associative Memory with Huge Storage Capacity

机译:在具有巨大存储容量的关联内存模型上

获取原文
获取原文并翻译 | 示例
           

摘要

In Krotov et al. (in: Lee (eds) Advances in Neural Information Processing Systems, Curran Associates, Inc., Red Hook, 2016) Krotov and Hopfield suggest a generalized version of the well-known Hopfield model of associative memory. In their version they consider a polynomial interaction function and claim that this increases the storage capacity of the model. We prove this claim and take the "limit" as the degree of the polynomial becomes infinite, i.e. an exponential interaction function. With this interaction we prove that model has an exponential storage capacity in the number of neurons, yet the basins of attraction are almost as large as in the standard Hopfield model.
机译:在Krotov等人。 (如:lee(eds)神经信息处理系统的进步,Curran Associates,Inc。,Red Hook,2016)Krotov和Hopfield建议了一个众所周知的关联内存的广义版本。 在他们的版本中,他们考虑多项式交互功能,并声称这增加了模型的存储容量。 我们证明了这一主张,并采取“极限”随着多项式变为无限的,即指数交互功能。 通过这种相互作用,我们证明了该模型具有指数储存能力在神经元的数量中,但吸引力的盆地几乎与标准Hopfield模型一样大。

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