Performance in Neural Network Training
显示 更早的评论
hi! just to clear up my confusion. Is 'Validation Check' in training parameter affects the training performance?
回答（1 个）
Greg Heath
2017-5-8
0 个投票
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
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
2017-5-7
2017-5-8
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
