Matlab 神经网络权重

Matlab 神经网络权重,matlab,neural-network,Matlab,Neural Network,这将是一个很长的问题: 我已经在MATLAB中编写了一个代码,用于用一个隐藏层更新MLP的权重。代码如下: function [ weights_1,weights_2 ] = changeWeights( X,y,weights_1,weights_2,alpha ) %CHANGEWEIGHTS updates the weight matrices % This function changes the weight of the weight matrix % for a gi

这将是一个很长的问题:

我已经在MATLAB中编写了一个代码,用于用一个隐藏层更新MLP的权重。代码如下:

function [ weights_1,weights_2 ] = changeWeights( X,y,weights_1,weights_2,alpha )
%CHANGEWEIGHTS updates the weight matrices 
%   This function changes the weight of the weight matrix
%   for a given value of alpha using the back propogation algortihm

m = size(X,1) ;     % number of samples in the training set

for i = 1:m
    % Performing the feed-forward step 
    X_i  = [1 X(i,1:end)]    ;  % 1-by-5 input 
    z2_i = X_i*weights_1'    ;  % 1-by-4   
    a2_i = sigmoid(z2_i)     ;  % 1-by-4   
    a2_i = [1 a2_i]          ;  % 1-by-5   
    z3_i = a2_i*weights_2'   ;  % 1-by-3   
    h_i  = sigmoid(z3_i)     ;  % 1-by-3   

% Calculating the delta_output_layer 
    delta_output_layer = ( y(i)' - h_i' )...
        .*sigmoidGradient(z3_i')  ; % 3-by-1 matrix

% Calculating the delta_hidden_layer 
    delta_hidden_layer =  (weights_2'*delta_output_layer)...
        .*sigmoidGradient([1;z2_i']) ; % 5-by-1 matrix 
    delta_hidden_layer = delta_hidden_layer(2:end) ; 

% Updating the weight matrices
    weights_2 = weights_2 + alpha*delta_output_layer*a2_i ; 
    weights_1 = weights_1 + alpha*delta_hidden_layer*X_i  ;
end

end
现在我想在MATLAB中提供的
fisherris
数据集上测试它,该数据集可以通过
load fisherris
命令访问。我将
meas
重命名为
X
,并将
species
更改为
150×3
矩阵,其中每行描述物种名称(例如,第一行是
[1 0]

我使用以下函数计算输出层的误差:

function [ g ] = costFunction( X,y,weights_1,weights_2 )
  %COST calculates the error 
  %   This function calculates the error in the 
  %   output of the neural network 

  % Performing the feed-forward propogation
  m = size(X,1) ; 
  X_temp  = [ones([m 1]) X]   ;  % 150-by-5 matrix 
  z2 = X_temp*weights_1'       ; % 150-by-5-by-5-by-4 
  a2 = sigmoid(z2)       ; 
  a2 = [ones([m 1]) a2]            ; % 150-by-5
  z3 = a2*weights_2'     ; % 150-by-3
  h  = sigmoid(z3)       ; % 150-by-3

  g = 0.5*sum(sum((y-h).^2)) ; 
  g = g/m ; 
end

现在在课程中,教授给出了一个玩具网络的例子,有3次迭代,我在这个网络上测试了这个,它给出了正确的值,但是当我在Fisherris数据上测试它时,成本不断增加。我不知道哪里出了问题。

输出数据的范围是什么?输出数据是一个[x y z]形式的向量,其中x,y,z属于{0,1}