Viewing profile — jeffclune
jeffclune
HN member- Joined
- Sat, Jun 18, 2011, 7:42 PM UTC
- HN karma
- 67
- Public activity
- 26 items
- HN profile
- View on Hacker News ↗
About jeffclune
No profile information was provided.
Recent public activity
-
comment
Comment #16603028
Hello all. We hope you enjoy the paper. Here are two fun gifs of clever solutions AI came up with: https://twitter.com/jeffclune/status/974718199722795008 https://twitter.com/jeffc…
- story
-
comment
Comment #15983793
Hello all. I am one of the paper's coauthors. Thank you for your interest in this work! We hope you enjoy it. Just an FYI, this paper is part of a cluster of five papers released o…
-
story
Uber AI Labs is Hiring Scientists Join us to create AI that moves the world
Hello all. We are hiring bright, passionate, creative, hard-working scientists to join us in San Francisco. Please click here to find out more: https://www.uber.com/info/ailabs/ Ab…
-
comment
Comment #9258793
No, it does not. See my reply to similar comments.
-
comment
Comment #9258779
I would just unleash evolution. 1 or 2 in the first generation is a toehold, and from there evolution can begin to do its work. You can also try a larger population (e.g. 2000) and…
-
comment
Comment #9253116
> Likewise, I was not very surprised that you can produce fooling images, but it is surprising and concerning that they generalize across models. It seems that there are entire, hu…
-
comment
Comment #9253101
See above. These images were accepted to a juried art competition and posted in a museum: http://www.evolvingai.org/share/20150213_184537.jpg
-
comment
Comment #9253096
Here they are: http://www.evolvingai.org/fooling There is also a video summary of the paper there.
-
comment
Comment #9253073
The paper does not use the weights of the network to produce (nearly all of) these images (see the responses to Karpathy above).
-
comment
Comment #9253053
In fact, we submitted them to an art competition and they were accepted and put up in a museum! http://www.evolvingai.org/share/20150213_184537.jpg
-
comment
Comment #9253016
Also, you don't necessarily need a lot of predictions from a net to fool it, because (another surprising result) images that fool one net tend to fool others! So I can create fooli…
-
comment
Comment #9253006
You say that these images are highly optimized to produce this effect and would not occur by chance, but have you looked at the images in the "fooling" paper? http://www.evolvingai…
-
comment
Comment #9252994
Surprisingly, ensembles do not really help. We have tried this and it does not work (the final paper for CVPR 2015 will show these results). Also see the work of Szegedy et al. and…
-
comment
Comment #9252979
Ha. Jason and I were typing at the same time. :-)
-
comment
Comment #9252978
They would look like optical illusions!
-
comment
Comment #9252972
Hi Andrej, I agree with most of what you say, but note that nearly all of the images in the paper were generated without the gradient. I.e. all the images produced by evolution did…
- story
-
comment
Comment #2900598
Sorry. The site is getting hammered right now due to the press articles and Hacker News. We just did a bit of hacking and hopefully it will work now!
-
comment
Comment #2900587
No. People just tend to choose ones that are. Here are some that are mostly bilaterally symmetrical, but with left-right asymmetry. http://endlessforms.com/o/69562/ (ghost) http://…
- comment
-
comment
Comment #2900227
Here is a longer article, with pictures of evolved objects printed in Silver and Bronze: http://www.physorg.com/news/2011-08-endless-web-d-printable....
-
comment
Comment #2900179
That's because you know how to use Blender, which most people don't. But the site is not for a situation when you have a specific design in mind, instead it is for when you want to…
-
comment
Comment #2697207
I noticed a surge in traffic to EndlessForms.com and realized it was coming from this post. Thanks to Joel for mentioning our site[1]! For those of you that don't know what I am ta…
-
comment
Comment #2669512
You can control the rotation with your arrow keys. Does that accomplish what you want? We need to make that more obvious. Thanks for the feedback!