...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Electronics and Communications in Japan. Part 2, Electronics >Autocorrelation Associative Memory Using Refractory Period of Neurons
【24h】

Autocorrelation Associative Memory Using Refractory Period of Neurons

机译：使用神经元不应期的自相关联想记忆

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In autocorrelation associative memory, a monotonic activation function is used from the viewpoint of network stability. The problems arise that the memory capacity is reduced and false memory can be generated, although the structure is simplified. This paper proposes a new memory model in which the associative ability is improved, while the conventional monotonic activation function is used in the autocorrelation associative memory model. In the proposed model, the refractory period is defined in the neuron, and the same convergence of the network as in the Hopfield model is always guaranteed. In the case of the discrete-time model, the proposed model with the refractory period T = 1 is equivalent to the case of a ternary nonmonotonic activation function. In other words, the proposed model can be regarded as a model including the nonmonotonic activation function model. The following results are shown by numerical experiment. As a discrete-time discrete-value model, the proposed model has a higher associative ability than the Hopfield model. As a continuous-time continuous-value model, when the refractory period is long, the associative ability is greater than that of the Hopfield model guaranteeing the same convergence. When the refractory period is short, the associative ability is further improved.
机译：在自相关联想存储器中，从网络稳定性的角度来看，使用单调激活函数。尽管简化了结构，但出现的问题是减小了存储容量并可能产生伪存储。本文提出了一种新的记忆模型，该模型提高了联想能力，而传统的单调激活函数被用于自相关联想记忆模型。在提出的模型中，不应期在神经元中定义，并且始终保证网络与Hopfield模型相同的收敛性。在离散时间模型的情况下，所建议的具有不应期T = 1的模型等效于三元非单调激活函数的情况。换句话说，提出的模型可以被认为是包括非单调激活函数模型的模型。数值实验表明以下结果。作为离散时间离散值模型，该模型具有比Hopfield模型更高的关联能力。作为连续时间连续值模型，当不应期较长时，关联能力要大于保证相同收敛性的Hopfield模型。不应期短时，缔合能力进一步提高。

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