1
$\begingroup$

From what I've learned about autoencoder is it takes an input and predicts an output almost similar to the input. So, if it outputs the same thing with the same dimensions, what is the benefit of using autoencoder then? We can directly work with the inputs.

$\endgroup$
  • $\begingroup$ three terms are you answer: Unsupervised Representation Learning $\endgroup$ – user3639557 Apr 6 at 12:18
1
$\begingroup$

You're correct that an auto-encoder outputs the same dimension as the input, but it goes through a smaller hidden layer. Imagine a series of layers, from input to output, each with the following number of neurons:

1000 : 500 : 100 : 500 : 1000

The 1000-dimensional input is squeezed through a 100-dimensional middle layer. Once trained, if you remove the last two layers, and only use:

1000 : 500 : 100

the 100-dimensional middle is a reduced dimensional representation, pure an encoding. You could use that as input to another learning method - another neural network or something else.

Think of it like PCA in which you only use the first few PCs. Principal components regression works in this way, but uses a linear projection of the data to lower dimensions, whereas the auto-encoder uses a non-linear protection.

| cite | improve this answer | |
$\endgroup$
  • $\begingroup$ Thanks, got it. $\endgroup$ – NoobySavage Apr 7 at 7:27

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