refine mlp

chapter05/mlp.m

@@ -1,17 +1,15 @@
-function [model, mse] = mlp(X, Y, h, eta)
+function [model, mse] = mlp(X, T, h)
 % Train a multilayer perceptron neural network
 % Input:
 %   X: d x n data matrix
-%   Y: p x n response matrix
+%   T: p x n response matrix
 %   h: L x 1 vector specify number of hidden nodes in each layer l
 % Ouput:
 %   model: model structure
 %   mse: mean square error
 % Written by Mo Chen ([email protected]).
-if nargin < 4
-    eta = 1/size(X,2);
-end
-h = [size(X,1);h(:);size(Y,1)];
+eta = 1/size(X,2);
+h = [size(X,1);h(:);size(T,1)];
 L = numel(h);
 W = cell(L-1);
 for l = 1:L-1
@@ -24,10 +22,10 @@
 for iter = 1:maxiter
 %     forward
     for l = 2:L
-        Z{l} = sigmoid(W{l-1}'*Z{l-1});
+        Z{l} = sigmoid(W{l-1}'*Z{l-1});   % 5.10, 5.49
     end
 %     backward
-    E = Y-Z{L};
+    E = T-Z{L};
     mse(iter) =  mean(dot(E,E),1);
     for l = L-1:-1:1
         df = Z{l+1}.*(1-Z{l+1});