Does this convolution use tied weights (for the encoder and decoder layers)? If so, is there a way to untie the weights? I'm curious about how to tie and untie the weights of the autoencoder and experiment with both.
This code doesn't use tied weights. If you want to experiment with that I'd recommend looking at the official theano code for an autoencoder. I personally haven't seen much evidence that it really makes a difference.
Does this convolution use tied weights (for the encoder and decoder layers)? If so, is there a way to untie the weights? I'm curious about how to tie and untie the weights of the autoencoder and experiment with both.