python 神经网络包 NeuroLab

neurolab模块相当于Matlab的神经网络工具箱(NNT)

neurolab模块支持的网络类型：

• 单层感知机(single layer perceptron)
• 多层前馈感知机(Multilayer feed forward perceptron)
• 竞争层(Kohonen Layer)
• 学习向量量化(Learning Vector Quantization)
• Elman循环网络(Elman recurrent network)
• Hopfield循环网络(Hopfield recurrent network)
• 卷边循环网络(Hemming recurrent network)

这里以多层前馈网络为例：neurolab.net.newff(minmax, size, transf=None)

Parameters:	minmax: list of list, the outer list is the number of input neurons, inner lists must contain 2 elements: min and max Range of input value size: the length of list equal to the number of layers except input layer, the element of the list is the neuron number for corresponding layer Contains the number of neurons for each layer transf: list (default TanSig)