Is it OK to increase validation checks and decrease min gradient while training neural network?

Kshitij Singh answered . 2025-07-30 12:47:45

 mse(ytst-ttst)/var(ttst,1) <= 0.01

 MSEgoal = max( 0, 0.01*(Ntrneq-Nw)*var(ttrn,0)/Ntrneq )
 MinGrad = MSEgoal/100
 net.trainParam.goal     = MSEgoal ;
 net.trainParam.min_grad = MinGrad ;

 [ I N ] = size(input) %  [ 85 130 ]
 [ O N ] = size(target)%  [ 26 130 ]

 Ntrn   = N-2*round(0.15*N) %   90 training examples
 Ntrneq = Ntrn*O            % 2340 training equations

 % Nw = (I+1)*H+(H+1)*O       % Number of unknown weights
 % For a robust design desire Ntrneq >> Nw or
 % H << Hub = -1+ceil( (Ntrneq-O) / (I+O+1)) % 20

 Hmax = 20
 dH   = 2
 Hmin = 1
 Ntrials = 10

 Design many nets and choose the best using the validation set performance.

 for h = Hmin:dH:Hmax
  ....
     for i = 1: Ntrials
  ... 
     end
 end

 greg Ntrials

Not satisfied with the answer ?? ASK NOW