Performance comparison plotting for different Back propagation algorithms

I am implementing various Backpropagation algorithms for the same dataset and trying to compare the performance. I got a help from the following tutorial for the same.

https://nl.mathworks.com/help/nnet/ug/choose-a-multilayer-neural-network-training-function.html

I tried to plot:

1.mean square error versus execution time for each algorithm 2.time required to converge versus the mean square error convergence goal for each algorithm

Have used the following code, to create my neural network and willing to know how can i implement the above two plots.

[x, t] = bodyfat_dataset;
net = feedforwardnet(10, 'trainlm');
net = train(net, x, t);
y = net(x);

Answer 1

[Santhana Raj]

You have to calculate the mean square error and time taken. You can use (t-y) to calculate the error and tic/toc to calculate the time taken. With this, you can plot a scatter plot for different algorithms.

For the second plot, in the properties of net, you can set the convergence goal. Change it in every iteration and as before use tic & toc to calculate the time taken. With that you can plot your required graph.

[Marimuthu Ananthavelu]

Thank you.

Answer 2

[Greg Heath]

Your stopping criterion for regression should be a fraction of the mean target variance. I tend to choose 0.01 (Rsquare = 0.99) for regression and 0.001 or 0.005 for time-series. For example,

 Msegoal = 0.01 * mse(t-y)/ vart1

where

vart1 = mean(var(target',1))

Hope this helps.

Greg

[Marimuthu Ananthavelu]

Thanks very much for your details.