Question
My input vector is a 130*85 matrix and my target vector is 130*26 matrix. I am using the below parameters for training the network with 60 hidden nodes. net.trainParam.max_fail = 50; net.trainParam.min_grad=1e-10; net.trainParam.show=10; net.trainParam.lr=0.01; net.trainParam.epochs=1000; net.trainParam.goal=0.001;` As you can see I have set the max_fail to 50 and min_grade to 1e-10. While the default values will be 6 and 1e-5 respectively. But with the default values, the training stops early with out reaching the performance goal. By setting these parameters,the training is stopped when the performance goal is reached. So. Is it OK to change these parameters?
Expert Answer
Kshitij Singh
PhD Expert
Answered Aug 11, 2026
The most important objective is to obtain an acceptable ratio of mean-square error to mean-target-variance for RANDOM subsets of NONTRAINING data. I find the best way to do this is to try to find the smallest value of H (No. of hidden layer nodes) that will yield
mse(ytst-ttst)/var(ttst,1) <= 0.01
i. e., 99% of a random test target subset variance is successfully modeled.
In order to do this I use the default 70/15/15 trn/val/tst data division and the training data goals
MSEgoal = max( 0, 0.01*(Ntrneq-Nw)*var(ttrn,0)/Ntrneq ) MinGrad = MSEgoal/100 net.trainParam.goal = MSEgoal ; net.trainParam.min_grad = MinGrad ;
For an I-H-O node topology obtained from N pairs of I-dimensional inputs and O-dimensional targets
[ 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
I have posted many, many examples on the NEWSGROUP and ANSWERS, Search on
greg Ntrials
100% Run Guarantee
3-Hour Fast-Track Delivery
Need a Custom Version or Complete Simulation for This Problem?
Our 500+ PhD engineers build, debug, and optimize working MATLAB scripts and Simulink (.slx) models tailored to your exact assignment rubrics with zero plagiarism.
Tested on MATLAB R2024b / R2026a
Turnitin 0% Plagiarism Report
Free 7-Day Revisions Guarantee
Have a different question? Ask here
Related neural network Questions & Solutions
Browse All →
Explore similar technical troubleshooting questions and verified MATLAB solutions:
Ready-to-Run MATLAB & Simulink Projects
Browse All Projects →