【摘要】 人工神经网络(ANN)中普遍采用的神经元模型具有单调有界的I／O特性,该文称其为近线性神经元(ALN,approximate－linear neuron),ALN既简化了网络的复杂性,也是限制ANN能力的一个瓶径.通过比较Hopfield神经网络的稳定性和Conway生命游戏的复杂行为,该文提出非线性神经元(NLN,non－linear neuron)的概念,其I／O特性是完全非线性的.ALN可以进一步提高ANN的非线性,从而增强它的功能,余数制神经网络是一个例子.更多还原

【Abstract】 ： In an artificial neural network,the property of the neuron model normally is monotone and bounded.This paper names it as approximate－linear neuron(ALN).It simplifies the complexity of the neural network,at the same time,becomes a bottleneck that limits the network＇s abilities.In contrast,by comparing the stability of Hopfield neural network with the aplenty behavior of Conway＇s life game,this paper preferred a new concept,non－linear neuron(NLN),which I／O property is non－linear completely.NLN can enhance the non－linear properties of ANN,so an ANN with NLN will be more powerful.Remainder ANN is an example．更多还原