2
$\begingroup$

I'm completely a noob in auto-encoder and deep learning thing. And now I'm trying to implement a simpe auto-encoder.

What I want to ask is: If given same dataset, will auto encoder produce the same optimum weight?

Thanks for your help

Improve this question
$\endgroup$
2
  • 1
    $\begingroup$ It depends upon your weight initialization and your training algorithm. If you use the same initial weights each time, use a deterministic training algorithm, and do not change the order in which your training data is fed into your algorithm, then I believe you should come up with the same results. $\endgroup$
    – John Yetter
    Commented Dec 9, 2015 at 2:05
  • 1
    $\begingroup$ @John Yetter I use L-BFGS for training. If I randomize the initial weight, then it's normal if i always get different weight, right? Thanks for your response $\endgroup$
    – MCRmy
    Commented Dec 9, 2015 at 2:16

1 Answer 1

Reset to default
1
$\begingroup$

Partially answered in comments:

It depends upon your weight initialization and your training algorithm. If you use the same initial weights each time, use a deterministic training algorithm, and do not change the order in which your training data is fed into your algorithm, then I believe you should come up with the same results. – John Yetter

( I use L-BFGS for training. If I randomize the initial weight, then it's normal if i always get different weight, right? Thanks for your response – MCRmy )

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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