I'm reading up some material on autoencoders . As far I've understood I can use them as a mechanism for dimensionality reduction. We can do dimensionality reduction for non-linear data as well.

If this is the case then if I build an autoencoder with just one node between Encoder and decoder layers possibly very high dimensional data. Can we represent the whole data with one node? If so will this be prone to overfitting.


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.