Performance comparison plotting for different Back propagation algorithms

조회 수: 2 (최근 30일)
Marimuthu Ananthavelu
Marimuthu Ananthavelu 2017년 5월 4일
댓글: Marimuthu Ananthavelu 2017년 5월 9일
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);

이 질문에 답변하려면 로그인하십시오.

채택된 답변

Santhana Raj
Santhana Raj 2017년 5월 4일
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.

추가 답변 (1개)

Greg Heath
Greg Heath 2017년 5월 6일
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

카테고리

Help Center 및 File Exchange에서 Define Shallow Neural Network Architectures에 대해 자세히 알아보기

태그

제품

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by