MATLAB Answers

How do validation check work in Neuralnet ?

262 views (last 30 days)
R G
R G on 7 Aug 2017
Commented: Moritz Hesse on 2 May 2019
I'm learning about the neural network in MATLAB. when I learn about the neural net, I don't see anything about validation check (usually data is divided by 2 training and test testing) but in Matlab, they have a part for validation and have Validation check(in figure = 6).
so what I want to know is why we need validation check and how it work to check

  0 Comments

Sign in to comment.

Accepted Answer

Greg Heath
Greg Heath on 7 Aug 2017
Edited: Greg Heath on 11 Jul 2018
design = train + validate
train : Weight Estimation
validate: Not directly involved in weight estimation. Protects ability to generalize to nontraining data. Stops training when the nontraining val subset error rate increases CONTINUOUSLY for more than 6 (default) epochs.
val subset error rate is therefore SLIGHTLY biased.
test subset error rate is COMPLETELY unbiased
default division ratio = 0.7/0.15/0.15
If val stopping occurs, take a look at the error rate curves and you will see why training was stopped.
OBVIOUSLY, the most unbiased approach for constant timestep timeseries prediction is to use DIVIDEBLOCK data division with the validation subset in the middle.
Hope this helps
Thank you for formally accepting my answer
Greg

  8 Comments

Show 5 older comments
ErikaZ
ErikaZ on 10 Jul 2018
Hi Greg, I am using DIVIDEBLOCK data division for my NARX net. Can you explain briefly why "val stopping is the most important for timeseries design using DIVIDEBLOCK data division"? Thanks.
Greg Heath
Greg Heath on 11 Jul 2018
Thanks for the heads up! Changed to:
OBVIOUSLY, the most UNBIASED approach for constant timestep timeseries prediction is to use DIVIDEBLOCK data division with the validation subset in the middle.
GREG

Sign in to comment.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!