Stochastic Resonance in Recurrent Neural Network with Hopfield-Type Memory
Stochastic Resonance in Recurrent Neural Network with Hopfield-Type Memory
复制标题
DOI：
10.1007/s11063-009-9115-3
复制
发表时间：
2009-10
影响因子：
3.1
通讯作者：
N. Katada;H. Nishimura
中科院分区：
文献类型：
--
作者：
N. Katada;H. Nishimura
随机共振（SR）是一种噪声的存在有助于非线性系统放大弱（在屏障下）信号的现象。本文研究了在随机动力学条件下，具有Hopfield型记忆的自联想神经网络的SR行为是如何被观察到的。我们专注于SR反应在两个系统，其中包括3个和156个神经元。这些情况被认为是有效的双井和多井模型。实验结果表明，该神经网络能够增强由存储模式序列组成的弱阈下信号，并具有较高的刺激与反应的一致性。
Stochastic resonance (SR) is known as a phenomenon in which the presence of noise helps a nonlinear system in amplifying a weak (under barrier) signal. In this paper, we investigate how SR behavior can be observed in practical autoassociative neural networks with the Hopfield-type memory under the stochastic dynamics. We focus on SR responses in two systems which consist of three and 156 neurons. These cases are considered as effective double-well and multi-well models. It is demonstrated that the neural network can enhance weak subthreshold signals composed of the stored pattern trains and have higher coherence abilities between stimulus and response.