Hopfield神经网络模型的恢复特性

RETRIEVAL PROPERTIES OF HOPFIELD NEURAL NETWORK MODELS

通过引入不同概率的双峰无规神经激活阈分布,来考虑对神经网络“记忆”恢复特性的影响,结果表明即使储存模式数超过孤立Hopfield模型的临界值α_c时系统仍然能成功地恢复储存信息。

In this paper, we propose a bimodal distribution of random neuronal activity threshold with different probabilities, to consider the influences on the retrieval properties of neural network. It is shown that the system successfully retrieves information even if the number of stored patterns exceeds the critical value of the pure Hopfield model.