2
$\begingroup$

Seems like Autoassociative neural networks and Autoencoders do the same thing.

Are they the same, or is there some subtlety I'm not picking up on?

$\endgroup$
5
$\begingroup$

The "autoassociative" paper is from 1992. The field had not settled on the term "autoencoder" for this concept.

$\endgroup$
1
$\begingroup$

Autoencoders need at least 1 hidden layer to be constructed.

But, Autoassociative neural networks could be obtained through a bidirectional associative memory, which is implemented with no hidden layer, and whose weights are learned in one step.

$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.