Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction
Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction
复制标题
DOI：
10.1109/ijcnn.2008.4634234
复制
发表时间：
2008-01
期刊：
影响因子：
--
通讯作者：
G. Tanaka;K. Aihara
中科院分区：
文献类型：
--
作者：
G. Tanaka;K. Aihara
复正负号函数作为复值递归神经网络的激活函数，在多状态联想记忆中得到了广泛的应用。本文提出了两种可供选择的具有循环性的激活函数。一种是基于定义在圆上的多级sigmoid函数的复sigmoid函数。另一个是由圆形图表示的分叉神经元的特性。研究了具有这两种激活函数的复值神经网络在多状态联想记忆测试中的性能。在这两个网络中，存储记忆模式的连接权重由广义投影规则确定。我们还证明了灰度图像重建所提出的方法作为一个可能的应用。
The complex-signum function has been widely used as an activation function in complex-valued recurrent neural networks for multistate associative memory. This paper presents two alternative activation functions with circularity. One is the complex-sigmoid function based on a multilevel sigmoid function defined on a circle. The other is a characteristic of a bifurcating neuron represented by a circle map. The performance of the complex-valued neural networks with the two kinds of activation functions is investigated in multistate associative memory tests. In both networks, the connection weights to store the memory patterns are determined by the generalized projection rule. We also demonstrate gray-level image reconstruction as a possible application of the proposed methods.