Onset of 'super retrieval phase' and enhancement of the storage capacity in neural networks of nonmonotonic neurons
Onset of 'super retrieval phase' and enhancement of the storage capacity in neural networks of nonmonotonic neurons
复制标题
非单调神经元神经网络中“超级检索阶段”的开始和存储容量的增强
DOI：
10.1088/0305-4470/26/17/014
复制
发表时间：
1993
期刊：
影响因子：
--
通讯作者：
T. Fukai
中科院分区：
文献类型：
--
作者：
M. Shiino;T. Fukai
使用自洽信噪分析方法研究了具有连续时间动态的联想记忆模拟神经网络的非单调传递函数。对于突触耦合，假设具有无偏随机模式的 Hebb 学习规则。发现由于与局部场分布特性相关的相变而发生一种新现象。在新发现的阶段（作者称之为超级检索阶段）的检索状态中，局部场中的噪声消失，并且即使对于在局部学习规则下存储的大量记忆模式，也能确保无错误的记忆检索。获得存储容量作为表示传递函数的非单调性程度的参数的函数，结果也可以实现存储容量的增强。
Analogue neural networks of associative memory with continuous time dynamics are studied for nonmonotonic transfer functions using the method of self-consistent signal-to-noise analysis. The Hebb learning rule with unbiased random patterns is assumed for the synaptic couplings. A novel phenomenon is found to occur as a result of a phase transition concerning the property of the local field distribution. In retrieval states of the newly found phase which the authors refer to as the super retrieval phase, noise in the local field vanishes and the memory retrieval without errors ensures even for an extensive number of memory patterns stored under the local learning rule. The storage capacity is obtained as a function of the parameter representing the degree of nonmonotonicity of the transfer functions, with the result that an enhancement of the storage capacity can also occur.