论文部分内容阅读
给出一种通过适当地选择输入层与隐层间的连接权,来减少单隐层前馈型神经网络隐层节点的个数的方法.应用此方法,分析了具有两个隐层节点的标准单隐层网络的学习能力,并对二元和三元XOR问题中的权值的选择问题进行了详细的讨论.
A method is proposed to reduce the number of hidden nodes in a single hidden layer feedforward neural network by properly choosing the connection weights between input layer and hidden layer. Using this method, Standard single hidden layer network learning ability, and the choice of weights in binary and ternary XOR problems are discussed in detail.