In [98]:

    

import numpy as np
import theano
from theano import tensor as T


W_values = np.array([[1,1],[1,1]], dtype=theano.config.floatX)
bvis_values = np.array([0,0], dtype=theano.config.floatX)
bhid_values = np.array([0,0], dtype=theano.config.floatX)

W = theano.shared(W_values) # we assume that ``W_values`` contains the
                            # initial values of your weight matrix
bvis = theano.shared(bvis_values)
bhid = theano.shared(bhid_values)

trng = T.shared_randomstreams.RandomStreams(1234)

def OneStep(vsample, W, bhid, bvis) :
    hmean = T.nnet.sigmoid(theano.dot(vsample, W) + bhid)
    hsample = trng.binomial(size=hmean.shape, n=1, p=hmean)
    vmean = T.nnet.sigmoid(theano.dot(hsample, W.T) + bvis)
    return trng.binomial(size=vsample.shape, n=1, p=vmean,
                         dtype=theano.config.floatX)

sample = T.matrix()

values, updates = theano.scan(OneStep, sequences=sample, non_sequences = [W, bhid, bvis], n_steps=sample.shape[0])

gibbs10 = theano.function([sample], values, updates=updates)


    

In [99]:

    

tmp = np.array([[10,10],[-10,-10]], dtype = theano.config.floatX)


    

In [100]:

    

gibbs10(tmp)


    

    
Out[100]:





array([[ 1.,  1.],
       [ 1.,  0.]], dtype=float32)