How take weight values for P nad N in a BPN network for face recognition

P=[196    35   234   232    59   244   243    57   226; ...
 188    15   236   244    44   228   251    48   230; ...    
 246    48   222   225    40   226   208    35   234]'; ...
% testing images 
N=[196    35   234   232    59   244   243    57   226; ...
 188    15   236   244    44   228   251    48   230; ...    
 246    48   222   225    40   226   208    35   234]';...

% N=[208    16   235   255    44   229   236    34   247; ...
%    245    21   213   254    55   252   215    51   249; ...    
%    248    22   225   252    30   240   242    27   244]'; ...

% Normalization

P=P/256;
N=N/256;
% display the training images 
% targets
img=[196 35 234;
    232 59 244 ;
    243 57 226]';  

T=img/256;;

% targets
%  T=[0.8    0.06    0.9;
%     0.9    0.17    0.8;
%     0.9    0.13    0.9];
S1=90;   % number of hidden layers
S2=3;    % number of output layers (= number of classes)

can anyone explain me how here we have taken the values of image matrix(P,N) and why do we need to normalize it?

Answer 1

[Greg Heath]

Normalization helps to prevent large signals from causing bounded activation functions in the first hidden layer ( like tansig and logsig) from operating in the asymptotic end regions where derivatives are so small that training may be stalled.

Keeping singals in the "active" nonasymptotic regime also helps numerical stability (See the comp.ai.neural-nets FAQ ).

What you have written in your post is very confusing.

How many classes, c do you have?

How large are your training and test sets?

[I Ntrn] = size(xtrn) % I = 9?

[O Ntrn] = size(ttrn) % O = c

[I Ntst] = size(xtst)

[O Ntst] = size(ttst)

Are the columns in your target matrices columns from the c-dimensional unit matrix eye(c)?

The number of training equations is Neq = Ntrn*O

For a I-H-O node topology the number of unknown weights is Nw = (I+1)*H+(H+1)*O.

If you are training to convergence, Neq >= Nw is required but Neq >> Nw is desired to mitigate measurement errors and noise in addition to obtaining good generalization with performance on nontraining data. The first requirement yields the following upper bound on the number of hidden nodes, H.

Hub = floor((Neq-O)/(I+O+1))

The second requirement yields H << Hub.

If you need a larger value of H to obtain satisfactory performance, use "Early Stopping" with a validation set and/or use regulatization with the objective function MSEREG.

Hope this helps.

Greg