K-Sparse-AutoEncoder
K-Sparse-AutoEncoder copied to clipboard
Some problem about selection in latent space.
Hi, I am working on a similar project now. But from my opinion, when selecting k largest activations in latent vector(z), the operation "selection" is not differentiable, and might not be suitable for applying BP. Can you tell me how to deal with it or you simply use the ordinary back-propagation method?