• Can you briefly remind how auto-encoders work?
  • Auto-encoders are useful for denoising, but can they be used for compression? If yes, do you have an example of common compression system that could be implemented using auto-encoders?

1 Response to “Auto-encoders”

  1. 1 Gabriel Bernier-Colborne February 1, 2013 at 10:33

    An auto-encoder is a learning algorithm that maps the input to some representation of that input, and then attempts to reconstruct the input given that representation. They are used for denoising, but are not known to be a suitable technique for data compression.

Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: