11-01-2015 01:08 PM
11-07-2016 03:17 AM
The same happened to me. As long as I keep the Learning Rate below 0.26 it works.
I read in another thread (about 2010) that there was some kind of bug. I thought that by now this bug would be fixed but it seems it is not.
3 weeks ago
i checked the code, the error should only be thrown for negative learning rates? It's:
if (learningRate <= Double.MIN_VALUE)
throw new OperatorException("Cannot reset network to a smaller learning rate.");
are you running 7.X? Could you maybe post your process?
3 weeks ago - last edited 3 weeks ago
I came across this problem when providing support. I'm not sure if it is the same on your data, but try turning the parameter Decay on (if it is not yet set).
This should automatically decrease the learning rate to one where the error does not occur.
I also recommend changing the parameter on Optimise Grid to Ignore Errors (or put the NN inside a Handle Exception operator). This will allow you to test all the parameters you want without worry whether a parameter setting might fail or not.