Data Science Asked by Dhyana on March 18, 2021
I’m completely new to neural nets, and am trying to get a grasp of autoencoding. I understand the function of the decoder and encoder, but what does the arg min section and beyond mean? Why is it equal to both phi and psi? Feel free to be abundant in your explanation. Thanks!
The question seems more about notation than autoencoders:
$ a,b = argmin_{a,b}f(a,b)$ simply means that $a$ and $b$ are chosen to minimize $f$.
w.r.t. autoencoders, the argmin statement is saying that we want the decoding of the encoded data $X$ to be as similar as possible to the original $X$.
To represent "decoding of the encoding", we can use function composition: $psicircphi X$ which means $psi(phi(X))$, hence the decoding of the encoding of $X$.
So overall, we are saying that we choose the encoding and decoding functions to minimize the delta between input $X$ and encoded/decoded $X$.
Where the question asks:
what does the arg min section and beyond mean?
The latter half "and beyond" should be more specific.
Answered by Benji Albert on March 18, 2021
Get help from others!
Recent Questions
Recent Answers
© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP