Performance in Neural Network Training
1 view (last 30 days)
Show older comments
hi! just to clear up my confusion. Is 'Validation Check' in training parameter affects the training performance?
0 Comments
Answers (1)
Greg Heath
on 8 May 2017
The main function of the validation subset is to stop training if it's error rate increases continually for 6(default) straight epochs.
The reason? The purpose of designing a net is for it to be able to generalize by working well on nontraining data.
The secondary function is to choose the best of multiple (typically 10 to 20) designs.
Then a completely unbiased estimate of performance can be obtained via the test subset.
Hope this helps.
Thank you for formally accepting my answer
Greg
0 Comments
See Also
Categories
Find more on Deep Learning Toolbox in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!