function [Y,G,E,Y1]=TwoLayers2(Inp,Tar,W,NNP)


W=W(:)';

[np,ni]=size(Inp);

%	PWeigths --- pointer to the weights
%	PBias --- pointer to the current bias

PWeigths=1:ni;
PBias=ni*NNP(1)+1;

%	Obtain the weigths from the input to the first layer in
%	W1 and the bias for the first hidden layer in T1

for i=1:NNP(1)
  W1(:,i)=W(PWeigths)';
  PWeigths=PWeigths+ni;
end;

T1=W(PBias:PBias-1+NNP(1));

%	Xi is the net imput to the neurons in the i-th layer; Yi is the 
%	output of the neurons in the i-th layer; Deri is the derivate of
%	Yi w.r.t. Xi

X1=Inp*W1+ones(np,1)*T1;
Y1=ones(np,NNP(1))./(1+exp(-X1));
Der1=Y1.*(1-Y1);


teta=[ones(np,1) Y1]\Tar;

Y=[ones(np,1) Y1]*teta;


for i=1:NNP(1)
  Der1(:,i)=Der1(:,i)*teta(i+1);
end;

l=1;
PBias=(ni*NNP(1))+1;

for i=1:NNP(1)
  for j=1:ni
    G(:,l)=Der1(:,i).*Inp(:,j);
    l=l+1;
  end;
  G(:,PBias)=Der1(:,i);
  PBias=PBias+1;
end;

E=G'*(Y-Tar);