I have been reading lately on autoencoders a lot. I just wanted to summarize my understanding of denoising autoencoders. As far as I understand they can be

  1. Fully connected (in which case, they will be over-complete autoencoders)

  2. Convolutional

The reason I say it should be over-complete is that the objective is to learn new features and I think extra neurons in the latent layer would help. There is no reason to have a lesser number of neurons because compressing is not the objective. I just want to understand is this the right thinking.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.