News for hackers. Stuff that matters.
Re:Deep image prior 'learns' on just one image by theoh on Thursday November 30, 2017 @07:39PM (#15821022)
Truly, an occasion for this koan:

Sussman attains enlightenment

In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6.

“What are you doing?”, asked Minsky.

“I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied.

“Why is the net wired randomly?”, asked Minsky.

“I do not want it to have any preconceptions of how to play”, Sussman said.

Minsky then shut his eyes.

“Why do you close your eyes?”, Sussman asked his teacher.

“So that the room will be empty.”

At that moment, Sussman was enlightened.

http://www.catb.org/jargon/html/koans.html

Re:Deep image prior 'learns' on just one image by jacquesm on Thursday November 30, 2017 @10:44PM (#15821750)
If there ever was one this is it.
Re:Deep image prior 'learns' on just one image by thefalcon on Friday December 01, 2017 @12:32PM (#15825505)
Okay, I admit it, I'm not enlightened. Will somebody please Explain Like I'm 5?
Re:Deep image prior 'learns' on just one image by anchpop on Friday December 01, 2017 @02:44PM (#15826701)
Initializing a neural net with random weights =/= making a neural net with no preconceptions on how to play. It still has those preconceptions, you just don't know what they are.

Closing your eyes so you can't see the contents of a room =/= the room is empty. Not knowing what something is, is different from it not existing

Re:Deep image prior 'learns' on just one image by thefalcon on Tuesday December 05, 2017 @06:51PM (#15857321)
Thanks!