Can we say that overfitting occur in this plot?

Performance plot from ANN is obtained as shown below.Does overfitting happen here?

Answer 1

[Greg Heath]

This is a case of

               *OVERTRAINING AN OVERFIT NET*

There are at least 3 ways to avoid this:

 1. *DO NOT OVERFIT:* 

 Make sure that the number of unknown weights, Nw does not 
 exceed the number of training equations, Ntrneq.

 2. *DO NOT OVERTRAIN* 

 In particular, the problem is not necessarily the 
 overfitting. Overfitting is easily mitigated by NOT 
 OVERTRAINING

    a. Use a VALIDATION set to implement "EARLY STOPPING".

    b. Use "REGULARIZATION" via TRAINBR to implement 
       "BAYESIAN RREGULARIZATION"

 See

https://www.mathworks.com/matlabcentral/answers/280818-how-to-solve-overtrained-nn-with-validation-stop

Hope this helps.

Thank you for formally accepting my answer

Greg

[KAE]

What plot features indicate this overtraining is occurring, compared to the plot in the documentation, which is copied below?

[Greg Heath]

The increase in the val error rate (grn) for 6(default) continuous epochs (9 to 15) while the training error (blu) is still decreasing.

Hope this helps.

Greg

[KAE]

And in the first plot (original question), the val error rate only increases for 5 continuous epochs, during epoch 6-11, while the training error is decreasing. Since 5 is less than the default of 6, the first plot shows overtraining. Is this interpretation right?

[Greg Heath]

5 - 11 not 6 - 11

Greg