Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Understanding Aesthetics with Deep Learning

devblogs.nvidia.com

Post reply on HN
Print view View original

21–30 of 31 posts

Re: Understanding Aesthetics with Deep Learning

#21

Post by saltenhav »

Jurgen Schmidhuber has an interesting perspective on the rewarding aspects of art and music.

To paraphrase, "Artists (and observers of art) get rewarded for making (and observing) novel patterns: data that is neither arbitrary (like incompressible random white noise) nor regular in an already known way, but regular in way that is new with respect to the observer's current knowledge, yet learnable (that is, after learning fewer computational resources are needed to encode the data)".

In other words, enjoyment of art is about learning (easy) patterns. Schmidhuber likens "fun" to the improvement of an observer's ability to compress a scene.

The source is worth the read: http://people.idsia.ch/~juergen/creativity.html

Re: Understanding Aesthetics with Deep Learning

#22

Post by mccoyspace »

yusee wrote: post #19
zaaakk wrote: post #11

Earlier quoted context omitted.

read adorno

Have you read him? If so, why not synthesize his arguments so we can all understand?

Here goes: Aesthetic Theory is a posthumous book by German philosopher Theodore Adorno and is one of the most important works on aesthetics in 20th century philosophy. In it, he combines elements from Kant, Hegel and Marx. From Kant's 1790 work, Critique of Judgement, he draws on the idea of the Sublime and the notion that art has formal autonomy (which Adorno modifies). From Hegel, he takes a dialectical understanding of the ultimate goal or aim of art, and from Marx he approaches art as being inseparable from society as a whole.

He shows how art has a semi-autonomous 'truth-content' (a la Kant), but one that is always the product and embodiment of unresolved contradictions within the larger social fabric. (a la Hegel, and more so Marx).

Returning to the NVidia article at the root of this thread, this passage pops out as problematic (certainly for Adorno, but also in general): "In our case, we use supervised machine learning, with a dataset of photographs pre-categorized as aesthetically pleasing or not." There is a real sense of question-begging going on here. And Adorno would say that this approach forecloses the very fact that the definitional boundaries of these categories are constantly shifting and lack any real social stability.

edit: links.... http://www.upress.umn.edu/book-division/books/aesthetic-theo... http://plato.stanford.edu/entries/adorno/#4 http://plato.stanford.edu/entries/kant-aesthetics/

Re: Understanding Aesthetics with Deep Learning

#23

Post by posterboy »

d12345m wrote: post #13
randcraw wrote: post #6

Earlier quoted context omitted.

You have to wonder, though. Is it impossible that there's a "music theory" for images/paintings/art that explains the mechanics of what makes them more compelling vs less compelling? I suspect there is, at least to some degree. Obviously images convey much more information than music, so any theory that doesn't encompass the semantics of the subject will miss most of the signal. But is there a theory for the presenta…

Perhaps it's not quite analogous to music theory, but what you're describing in the first paragraph would be referred to as the formal elements of art or simply the elements of art. Analysis of these elements (form, line, space, color, and texture) is usually a part of the sort of art criticism you'd find in academic studio art, art history, or even just the New York Times art section. The visual design field has a s…

I heard the term Gestalt Laws, from a German loan word, used to describe this. I don't the relation of this to your notion.

http://www.dict.cc/?s=gestalt

https://en.wikipedia.org/wiki/Gestalt_psychology

Re: Understanding Aesthetics with Deep Learning

#25

Post by posterboy »

radarsat1 wrote: post #14
randcraw wrote: post #6

Earlier quoted context omitted.

You have to wonder, though. Is it impossible that there's a "music theory" for images/paintings/art that explains the mechanics of what makes them more compelling vs less compelling? I suspect there is, at least to some degree. Obviously images convey much more information than music, so any theory that doesn't encompass the semantics of the subject will miss most of the signal. But is there a theory for the presenta…

The problem is that you'll hit a wall when it comes to understanding "what makes art." You can do all the theory you want, and people do, of course. You can analyze all that has ever been done, and come up with rules for describing and even generating music and art. But there is no guarantee that these will allow you to predict what makes future art. Just like with financial markets, in art, what happened in the past…

> You can analyze all that has ever been done, and come up with rules for describing and even generating music and art.

No, you cannot recognize anything as art before you haven't layed out the rules to describe art.

>But there is no guarantee that these will allow you to predict what makes future art

Prediction from Samples is covered by the sampling theorem, which theoretically holds for periodic signals and an infinite amount of samples, only. Although, in practice the output from my soundcard is rather fine, and facial recognition software works, too.

Re: Understanding Aesthetics with Deep Learning

#26

Post by posterboy »

maldusiecle wrote: post #20
posterboy wrote: post #17

Earlier quoted context omitted.

We listen to foreign music a lot and still find pleasure in the voices. Although I'm mostly speaking from my experience with English before I had learned it, which is yet rather close to German, so YMMV > No True Scotsman thinks that subject matter is irrelevant fixed that for you

No idea what the No True Scotsman fallacy has to do with this; it involves dismissing an example, but no example was offered. You're welcome to offer one, if you'd like. We listen to foreign music and find pleasure in the voices because a voice itself is expressive, independent of language: a cry, a laugh, an imprecation. The same is true of light, shape, etc., but artists who work with these qualities independent of…

I was just pattern matching.

Re: Understanding Aesthetics with Deep Learning

#27

Post by ibuildthings »

kafkaesq wrote: post #24

A better title would have been "Using ML to rank and classify images according to aesthetics." Which in itself is quite impressive. But nowhere do we see indications that these algorithms "understand" the images, in any meaningful sense.

The author here. I used the term "understanding", not as in machines understanding the images, but more as scientific attempt in understanding aesthetics. ( "empowering me to develop systems for understanding images from a computational and scientific perspective" ).

Re: Understanding Aesthetics with Deep Learning

#28

Post by ibuildthings »

mccoyspace wrote: post #22
yusee wrote: post #19

Earlier quoted context omitted.

Have you read him? If so, why not synthesize his arguments so we can all understand?

Here goes: Aesthetic Theory is a posthumous book by German philosopher Theodore Adorno and is one of the most important works on aesthetics in 20th century philosophy. In it, he combines elements from Kant, Hegel and Marx. From Kant's 1790 work, Critique of Judgement, he draws on the idea of the Sublime and the notion that art has formal autonomy (which Adorno modifies). From Hegel, he takes a dialectical understandi…

Author here. Just to clarify, motive of this work is to ease curation, with the massive amount of content being created; but by no means an attempt at creativity or originality.

The work is not at all contradictory to Adorno, especially in the sense that it is explicitly trying to as non-reductionist as possible, and assuming notion of aesthetics is a dynamic entity .

There is a finite pattern in the dataset; more interesting, it has its interesting share of subtleties ( for example, as opposed to a image classification problems), and the technological question is whether we can capture these.

But there is another interesting data question. For our work, we curated our training set with the help of expert curators. But the dataset itself is a metamorphising entity; i.e. it is subject to revision ( it is a continuous process for us at the moment), but more interestingly it is a chance for open debate between our curators. In some sense, technology allow to codify and challenge our notion of aesthetics ( especially with the evolution in our training sets) at a given point of time.

Re: Understanding Aesthetics with Deep Learning

#29

Post by kafkaesq »

ibuildthings wrote: post #27
kafkaesq wrote: post #24

A better title would have been "Using ML to rank and classify images according to aesthetics." Which in itself is quite impressive. But nowhere do we see indications that these algorithms "understand" the images, in any meaningful sense.

The author here. I used the term "understanding", not as in machines understanding the images, but more as scientific attempt in understanding aesthetics. ( "empowering me to develop systems for understanding images from a computational and scientific perspective" ).

Fair enough -- thanks for clarifying.

Re: Understanding Aesthetics with Deep Learning

#30

Post by mccoyspace »

ibuildthings wrote: post #28
mccoyspace wrote: post #22

Earlier quoted context omitted.

Here goes: Aesthetic Theory is a posthumous book by German philosopher Theodore Adorno and is one of the most important works on aesthetics in 20th century philosophy. In it, he combines elements from Kant, Hegel and Marx. From Kant's 1790 work, Critique of Judgement, he draws on the idea of the Sublime and the notion that art has formal autonomy (which Adorno modifies). From Hegel, he takes a dialectical understandi…

Author here. Just to clarify, motive of this work is to ease curation, with the massive amount of content being created; but by no means an attempt at creativity or originality. The work is not at all contradictory to Adorno, especially in the sense that it is explicitly trying to as non-reductionist as possible, and assuming notion of aesthetics is a dynamic entity . There is a finite pattern in the dataset; more in…

Thanks for the followup. I enjoyed reading the article and it is a very interesting project and a great effort. I did read at the end that it was about how to amplify the efforts of the human curators -- a great problem to tackle.
Post reply on HN