Increasing the number of epochs to reach the performance goal

Illustration
dhmendra_singh - 2021-07-13T10:06:00+00:00
Question: Increasing the number of epochs to reach the performance goal

Hello, I am training the neural network with input vector of 85*650 and target vector of 26*650. Here is the list of parameters that I have used   net.trainParam.max_fail = 6; net.trainParam.min_grad=1e-5; net.trainParam.show=10; net.trainParam.lr=0.9; net.trainParam.epochs=13500; net.trainParam.goal=0.001; Number of hidden nodes=76 As you can see ,I have set the number of epochs to 13500. Is it OK to set the number of epochs to such a large number?. Performance goal is not reaching if the number of epochs is decreased and I am getting a bad classification while testing.

Expert Answer

Profile picture of Kshitij Singh Kshitij Singh answered . 2025-11-20

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

 Ntrn   = N - 2*round(0.15*N)% 90
 Ntrneq = Ntrn*O        %  2340 training equations
%Nw = (I+1)*H+(H_1)*O % unknown weights
 
% Ntrneq >> Nw, or equivalently, H << Hub where
 Hub = -1+ceil((Ntrneq-O) / (I+O+1))  % 20
Try to minimize I and H while using as many defaults as possible.
 
I don't remember ever having to incease the default numepochs.


Not satisfied with the answer ?? ASK NOW

Get a Free Consultation or a Sample Assignment Review!