Hi, did you solve this? Could you tell us how did you do it? I would appreciate it.
El martes, 8 de diciembre de 2015, 21:57:35 (UTC+1), J Zam escribió: > > Hi, > > This may have been asked before but I haven't found an answer for it in > the topics. I'm trying to apply dropout to an MLP with a linear regression > layer as output. My question is with regards to the dropout component, > after looking around, I have my dropout function as: > > def drop(input, rng, p=0.5): > > srng = RandomStreams(rng.randint(999999)) > > mask = srng.binomial(n=1, p=1.-p, size=input.shape) > return input * T.cast(mask, theano.config.floatX) / (1.-p) > > I'm not sure I understand correctly, but why is there a need to divide by > (1. -p) ? > > Also, I have been reading that there is a need for re-scaling of weights > when dropout is applied: > > > http://christianherta.de/lehre/dataScience/machineLearning/neuralNetworks/Dropout.php > http://arxiv.org/pdf/1207.0580v1.pdf (A.1) > > and I'm not sure at what step to do this or what is it that it > accomplishes. > > I'm trying to get my head around it and any help would be appreciate it. > > Thanks! > -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to theano-users+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
