MATLAB中的神经网络

我在Matlab中训练了xor神经网络并得到了这些权重:

iw: [-2.162 2.1706; 2.1565 -2.1688]

lw: [-3.9174 -3.9183]

b{1} [2.001; 2.0033]

b{2} [3.8093]

仅仅是出于好奇,我试图编写MATLAB代码来计算这个网络的输出(隐藏层中的2个神经元,输出中的1个,TANSIG激活函数).

我得到的代码:

l1w = [-2.162 2.1706; 2.1565 -2.1688];
l2w = [-3.9174 -3.9183];
b1w = [2.001 2.0033];
b2w = [3.8093];

input = [1, 0];

out1 = tansig (input(1)*l1w(1,1) + input(2)*l1w(1,2) + b1w(1));
out2 = tansig (input(1)*l1w(2,1) + input(2)*l1w(2,2) + b1w(2));
out3 = tansig (out1*l2w(1) + out2*l2w(2) + b2w(1))

问题是当输入是[1,1]时,它输出-0.9989,当[0,1] 0.4902时.虽然模拟用MATLAB输出生成的网络是充分的,但是0.00055875和0.99943.

我做错了什么？

我写了一个简单的XOR网络示例.我用过newpr,默认tansig为隐藏和输出层传递函数.

input = [0 0 1 1; 0 1 0 1];               %# each column is an input vector
ouputActual = [0 1 1 0];

net = newpr(input, ouputActual, 2);       %# 1 hidden layer with 2 neurons
net.divideFcn = '';                       %# use the entire input for training

net = init(net);                          %# initialize net
net = train(net, input, ouputActual);     %# train
outputPredicted = sim(net, input);        %# predict

然后我们通过自己计算输出来检查结果.需要记住的重要一点是,默认情况下,输入/输出会缩放到[-1,1]范围:

scaledIn = (2*input - 1);           %# from [0,1] to [-1,1]
for i=1:size(input,2)
    in = scaledIn(:,i);             %# i-th input vector
    hidden(1) = tansig( net.IW{1}(1,1)*in(1) + net.IW{1}(1,2)*in(2) + net.b{1}(1) );
    hidden(2) = tansig( net.IW{1}(2,1)*in(1) + net.IW{1}(2,2)*in(2) + net.b{1}(2) );
    out(i) = tansig( hidden(1)*net.LW{2,1}(1) + hidden(2)*net.LW{2,1}(2) + net.b{2} );
end
scaledOut = (out+1)/2;              %# from [-1,1] to [0,1]

或更有效地表示为一行中的矩阵产品:

scaledIn = (2*input - 1);           %# from [0,1] to [-1,1]
out = tansig( net.LW{2,1} * tansig( net.IW{1}*scaledIn + repmat(net.b{1},1,size(input,2)) ) + repmat(net.b{2},1,size(input,2)) );
scaledOut = (1 + out)/2;            %# from [-1,1] to [0,1]