声明:文中的两个案例matlab源码引用自网络,并非本人所写,在此感谢原作者。原链接http://wenku.baidu.com/view/d8df1821aaea998fcc220e03.html?from=search
1)traingd——梯度下降反向传播
traingd Gradient descent backpropagation.
traingd is a network training function that updates weight and
bias values according to gradient descent.
根据梯度下降法更新权值和偏置。
2)newff :前馈网络创建函数
newff Create a feed-forward backpropagation network.
3) train:训练网络
train Train a neural network.
[NET,TR] = train(NET,X,T) takes a network NET, input data X and target data T and returns the network after training it, and a a training record TR.
返回训练后的网络和训练记录TR
4)sim:利用网络进行仿真
sim Simulate a neural network.
sim(NET,X) takes a network NET and inputs X and returns the outputs Y generated by the network. This syntax is equivalent to NET(X).
返回由网络产生的输出。
5)matlab神经网络工具
设置隐藏层的神经元个数: