Neural network training Maximum mu reached

I am trying to train a neural network. Within first iteration itself it gives maximum mu reached. I have been reading at several places, that It is a sign of convergence. But the model generates a very high error of the order 10^4.

[Greg Heath]

Reaching maximum mu is not a sign of convergence

It is a sign that the training should be stopped because additional training will degrade learning.

Hope this helps

Thank you for formally accepting my answer

Greg.

Answer 1

[JESUS DAVID ARIZA ROYETH]

Hello, Matlab selects a default Mu value of 0.001, but you can change it using the command: Net.trainParam.Mu = 0.0001; With this command you can give the value you want before training neural red, if you are using nftool, you can go to the last session called "Save Result" and generate a simple script, and before the line train (net, x , T) change the value of MU, if the error persists, then you should try changing the number of neurons in the hidden layer, or the transfer function of your layers

[shaifali gupta]

Thanks!

Answer 2

[Greg Heath]

Reaching maximum mu is not a sign of convergence

It is a sign that the training should be stopped because additional training will degrade learning.

Hope this helps

Thank you for formally accepting my answer

Greg.

[Chris P]

Do you have any tips to avoid this?...