Mercurial > ift6266
diff deep/stacked_dae/v2/stacked_dae.py @ 228:851e7ad4a143
Corrigé une erreur dans la formule de coût modifiée dans stacked_dae, et enlevé des timers dans sgd_optimization
| author | fsavard |
|---|---|
| date | Fri, 12 Mar 2010 10:47:36 -0500 |
| parents | acae439d6572 |
| children | 02eb98d051fe |
line wrap: on
line diff
--- a/deep/stacked_dae/v2/stacked_dae.py Fri Mar 12 10:31:10 2010 -0500 +++ b/deep/stacked_dae/v2/stacked_dae.py Fri Mar 12 10:47:36 2010 -0500 @@ -133,7 +133,7 @@ # used later when stacking dAs. self.y = T.nnet.sigmoid(T.dot(self.tilde_x, self.W ) + self.b) # Equation (3) - self.z = T.nnet.sigmoid(T.dot(self.y, self.W_prime) + self.b_prime) + #self.z = T.nnet.sigmoid(T.dot(self.y, self.W_prime) + self.b_prime) # Equation (4) # note : we sum over the size of a datapoint; if we are using minibatches, # L will be a vector, with one entry per example in minibatch @@ -142,9 +142,9 @@ # bypassing z to avoid running to log(0) z_a = T.dot(self.y, self.W_prime) + self.b_prime - log_sigmoid = T.log(1) - T.log(1+T.exp(-z_a)) + log_sigmoid = T.log(1.) - T.log(1.+T.exp(-z_a)) # log(1-sigmoid(z_a)) - log_1_sigmoid = -self.x - T.log(1+T.exp(-z_a)) + log_1_sigmoid = -self.z_a - T.log(1.+T.exp(-z_a)) self.L = -T.sum( self.x * (log_sigmoid) \ + (1.0-self.x) * (log_1_sigmoid), axis=1 )