Class AEStack

source code

object --+    
         |    
     Model --+
             |
            AEStack

a stack of denoising autoencoders. Each layer is a denoising autoencoder. A denoising autoencoders tries to reconstruct the input from a corrupted version of it by projecting it first in a latent space and reprojecting it afterwards back in the input space. Please refer to Vincent et al.,2008 for more details. If x is the input then equation (1) computes a partially destroyed version of x by means of a stochastic mapping q_D. Equation (2) computes the projection of the input into the latent space. Equation (3) computes the reconstruction of the input, while equation (4) computes the reconstruction error.

.. math:

   ilde{x} ~ q_D(  ilde{x}|x)                                     (1)

  y = s(W  ilde{x} + b)                                           (2)

  x = s(W' y  + b')                                                (3)

  L(x,z) = -sum_{k=1}^d [x_k \log z_k + (1-x_k) \log( 1-z_k)]      (4)

this is a completely unsupervised model that concatenates autoencoders.