Designing Cities and Furnitures With Machine Learning | Two Minute Papers #36

Designing Cities and Furnitures With Machine Learning | Two Minute Papers #36


Dear Fellow Scholars, this is Two Minute Papers
with Károly Zsolnai-Fehér. Creating geometry for a computer game or a
movie is a very long and arduous task. For instance, if we would like to populate a virtual
city with buildings, it would cost a ton of time and money and of course, we would need
quite a few artists. This piece of work solves this problem in
a very elegant and convenient way: it learns the preference of the user, then creates and
recommends a set of solutions that are expected to be desirable. In this example, we are looking for tables
with either one leg or crossing legs. It should also be properly balanced, therefore if we
see any of these criteria, we’ll assign a high score to these models. These are the
preferences that the algorithm should try to learn. The orange bars show the predicted score for
new models created by the algorithm – a larger value means that the system expects the user
to score these high, and the blue bars mean the uncertainty. Generally, we’re looking for solutions with
large orange and small blue bars, this means that the algorithm is confident that a given
model is in line with our preferences. And we see exactly what were looking for – novel,
balanced table designs with one leg or crossed legs. Interestingly, since we have these uncertainty
values, one can also visualize counterexamples where the algorithm is not so sure, but would
guess that we wouldn’t like the model. It’s super cool that it is aware how horrendous
these designs looks. It may have a better eye than many of the contemporary art curators
out there. There are also examples where the algorithm is very confident that we’re going
to hate a given example because of its legs or unbalancedness, and would never recommend
such a model. So indirectly, it also learns how a balanced
piece of furniture should look like, without ever learning the concept of gravity or doing
any kind of architectural computation. The algorithm also works on buildings, and
after learning our preferences, it can populate entire cities with geometry that is in line
with our artistic vision. Thanks for watching and for your generous
support, and I’ll see you next time!

4 thoughts on “Designing Cities and Furnitures With Machine Learning | Two Minute Papers #36

  1. I've written a little excerpt about a similar Idea sveral DAYs ago:
    Smart Villages the bye

    It's the year 2016, the old ideas of the country rescue have already failed.
    The large corporations are now looking stem the exodus from the city for newer ways and
    were also more successful with it.
    The new issue of Siemens & Co. were now "Full Automated city".
    The idea was simple and compelling:
    Money saving through automation!
    And this approach should be implemented in the "FACs" with a radicalism as it should have ever seen no one.
    To be allowed to live in the first prototype was required to complete privacy waiver. In the sense that each First a GPS chip was missed.
    The deterrent due and to prevent any crimes.
    Because that only made work.
    Police costs money, so that's been flat.

    But who the conditions entered the new cities, as they were called in the vernacular, brought with them, who lived simply in paradise.

    Unconditional basic income at above-average wages were there Standart,
    since the entire 500,000 residents no more than 100 men needed to run.
    But 100 obligor who worked in exchange for a above-average wages were found quickly. And so I enrolled in the service of a better future for the service of 12 hours a week in one of the first "Full Automated Citys" Worldwide in …….

    PS: Seems like the ideas you publicate produce sth. like a "stream"-of-entanglement. But belive me i'm neither religious nor crazy atm. so probably it's a random thing.
    But hey, I'm on the next thing again so lets look what will happen.

Leave a Reply

Your email address will not be published. Required fields are marked *