News for hackers. Stuff that matters.

A comment on Technologists have produced a 3D-printed painting in the style of Rembrandt. Parent comment

Re:Technologists have produced a 3D-printed painting in the ... by nxzero on Thursday April 07, 2016 @10:19PM (#11452185)
Human artist would most likely inject their own take into "imitation" art, but if the computer's art was purely derived from an artist past work, it's only inspired by the artist work; this is in theory, even the code to enable this would most likely have biases that would result in artifacts in the "new" art.
[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by gus_massa on Thursday April 07, 2016 @10:44PM (#11452265)
From http://www.catb.org/jargon/html/koans.html#id3141241

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.

[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by Dylan16807 on Friday April 08, 2016 @01:15AM (#11452709)
Ugh. I see the point in general, but the eye closing is a really broken analogy, and there is a difference between a bias and a preconception.
[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by sp332 on Friday April 08, 2016 @10:16AM (#11454770)
It's not the case that randomly-generated weights will not have biases. The point is that if you generate weights randomly the computer will still have biases, you just don't know what they will be.
[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by nxzero on Friday April 08, 2016 @05:44AM (#11453569)
Yes, the difference between bias and preconception is exactly what, or are you being bias?

Seriously, lookup the meaning of the terms and see if what they mean are what you believe them to mean.

[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by Dylan16807 on Friday April 08, 2016 @12:28PM (#11455896)
A preconception is an idea. A bias is much more general. If you're putting in a table, and you don't make it quite flat, you have biased the table, but you have not instilled preconceptions in the table.
[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by nxzero on Thursday April 07, 2016 @10:46PM (#11452272)
Yes, I know, and agree.
[ Parent | on HN ]
Re:Technologists have produced a 3D-printed painting in the ... by tlarkworthy on Thursday April 07, 2016 @10:45PM (#11452267)
Only if the training set was the artists thoughts and feelings. And the model was his nervous system and body mechanics. The images alone are not enough data to truly mimick the next painting he would have produced. It's an average of the existing work.
[ Parent | on HN ]