ASSOCIATIVE MEMORY WITH HIGH INFORMATION-CONTENT
ASSOCIATIVE MEMORY WITH HIGH INFORMATION-CONTENT
复制标题
DOI：
10.1103/physreva.39.2689
复制
发表时间：
1989-03-01
影响因子：
2.9
通讯作者：
SCHULTEN, K
中科院分区：
文献类型：
--
作者：
BUHMANN, J;DIVKO, R;SCHULTEN, K
Hopfield的自适应阈值和抑制相互作用模型的扩展产生了一个能够几乎最佳地存储低活动模式的网络。给出了无噪声情况下平均场方程的复制对称解。证明了以下性质：对于低活性水平a，存储容量增加为-(a lna)−1；每个突触最多可存储0.38位；虚假的国家可以被压制；网络不是固执己见的，也就是说，它可以将输入分类为与存储的模式不够相似。
An extension of Hopfield’s model with adaptive threshold and inhibitory interactions yields a network capable of nearly optimal storage of patterns of low activity. A replica symmetric solution of the mean-field equations is presented for the noise-free case. The following properties are demonstrated: For a low level of activity a the storage capacity increases as-(a lna)− 1; up to 0.38 bits per synapse can be stored; spurious states can be suppressed; the network is not opinionated, ie, it can categorize inputs as not similar enough to patterns stored.