also what is the constant that cancels out, does it equate to vbias**2 On Monday, 16 December 2013 18:35:26 UTC, Nicolas Boulanger-Lewandowski wrote: > > You can use that term provided you remove the -(v dot vbias) term in the > original free energy function. > > The difference between the two formulation is then a constant that cancels > out when you subtract the negative phase, so you can use either. > > > > On Monday, December 16, 2013 1:55:31 AM UTC-5, C. Ng wrote: >> >> Hi Nicolas and all, >> >> I have also seen the additional free energy term written as >> 0.5*(v-vbias)**2).sum() >> >> Does it make a difference? >> >> >> >> >> On Tuesday, March 12, 2013 5:32:19 AM UTC+8, Nicolas >> Boulanger-Lewandowski wrote: >>> >>> Hi, >>> >>> The shared_normal and shared_zeros are simply convenience functions to >>> initialize weight and bias *parameters* respectively; they both return >>> float shared variables. >>> >>> For sequences of real-valued visible units, you can use the Gaussian >>> RBM. To adapt the code for Gaussian RBM, you need to alter two things: >>> >>> - Add 0.5*(v**2).sum() to the free energy >>> - Modify the sampling for v_i from Bernoulli to normal with variance 1 : >>> mean_v = T.dot(h, W.T) + vbias >>> v = mean_v + rng.normal(size=mean_v.shape, avg=0.0, std=1.0, >>> dtype=theano.config.floatX) >>> >>> You can also replace the monitoring cost to the L2 error: (v-mean_v)**2 >>> >>> >>> On Sunday, March 10, 2013 8:51:19 AM UTC-4, Alexander Bridi wrote: >>>> >>>> Hey all, >>>> >>>> I'm trying to modify the rnnrbm.py tutorial code to allow for >>>> non-binary inputs/outputs. >>>> >>>> So far, I found the modification must be made between the output of the >>>> RNN and the input of the RBM, possibly around the binary bh, bv, bu >>>> variables. >>>> >>>> I tried creating these variables via the shared_normal function (as >>>> opposed to the shared_zeros function), but I end up running into >>>> a ValueError around the IncSubtensor's dtype consistency. >>>> >>>> But more importantly, is this the right thing to do!? I have the >>>> feeling this isn't, because the shared_normal function just initializes >>>> the >>>> variable in a non-binary manor and doesn't play a role in the updates.. >>>> but >>>> I'm not sure how to modify the recurrence function to yield non-binary >>>> outputs/ >>>> >>>> Has anyone tried doing this already? >>>> >>>> Any advice would be much appreciated! >>>> >>>> Thanks, >>>> >>>> Alexander >>>> >>>
-- --- 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 [email protected]. For more options, visit https://groups.google.com/d/optout.
