how to fix constant iteration in neural networks
4 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Thirunavukkarasu
am 16 Sep. 2014
Kommentiert: Greg Heath
am 22 Dez. 2017
when i am trying to train my neural network using levenberg marquardt algorithm it shows different iteration at each times how do i fix my neural network with constant iteration period
3 Kommentare
Shreeja Shetty
am 20 Jul. 2017
I am currently facing a similar issue as mentioned above. Can someone please provide a solution.
Akzeptierte Antwort
Greg Heath
am 19 Sep. 2014
When you train your net again, the random number generator is in a different state. Therefore you will have a different trn/val/tst split AND a different set of initial weights. The training will stop according to one of several stopping rules including
1. performance goal achieved
2. maximum epochs reached
3. minimum gradient achieved
4. maximum mu reached
5. validation stop (validation performance reaches a local maximum)
[ net tr y e ] = train(net,x,t) % e=t-y
stopcriterion = tr.stop
or, if you are training in a double for loop
stopcriteria{i,j} = tr.stop
This is great because all are chosen to optimize your performance. That is why every time I try a new candidate for H=number of hidden nodes, I design at least Ntrials = 10 nets. So, if I am considering 10 different values for H, I will have 100 designs which I summarize in 3 10 by10 matrices for training, validation and test performance.
The best net is determined from the nontraining validation set performance (smaller values of H are preferred) and an unbiased estimate of unseen nontraining data performance is obtained from the test set performance.
Hope this helps.
Thank you for officially choosing my answer
Greg
0 Kommentare
Weitere Antworten (2)
Greg Heath
am 17 Sep. 2014
If you train multiple nets in a loop you can duplicate previous runs by keeping track of the state of the random number generator. That is why I always specify an initial random number state, before the outer loop. For examples, search on
greg rng(0)
or
greg rng('default')
Hope this helps.
Thank you for formally accepting my answer
Greg
5 Kommentare
Parul Singh
am 26 Apr. 2017
rng default- net gives different outputs each time it is run
rng (variable number) - number of iterations remain the same at 1000
We want to vary the number of iterations to achieve best output and then for a constant number of iterations, we want the network to get the same output each time it is nrun.
Please help.
Greg Heath
am 20 Jul. 2017
Given what I have learned in 37 years of NN design, what you want to do is illogical. Please reread what I have written.
Greg
Cesare Trematore
am 19 Dez. 2017
I do not know if I fully agree. I was running a pattern recognition neural network with the trainbr option. The train perfomance kept improving up to 1000 epochs, but after about 200 epochs the test perfomance started worsening. In this cases would be useful to have the option to stop the training after a prefixed number of epochs.
1 Kommentar
Greg Heath
am 22 Dez. 2017
That option is available.
However, why in the world are you using trainbr for pattern recognition?
What happens when you use patternet with all defaults except number of hidden nodes and initial RNG state?
Search the NEWSGROUP and ANSWERS with
greg patternnet
Hope this helps.
Greg
Siehe auch
Kategorien
Mehr zu Pattern Recognition and Classification finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!