-- Final Call for Papers -- ** AAAI 2013 Fall Symposium: “How Should Intelligence be Abstracted in AI Research: MDPs, Symbolic Representations, Artificial...
6092
Jeff Clune
jeffreyclune
May 13, 2013 11:48 pm
Hello all, I'm pleased to announce the following new paper on the "Seeded-CPPN Technique": Upload Any Object and Evolve it: Injecting Complex Geometric...
6091
joel278
May 8, 2013 6:28 am
Hi Jeff, I'm glad you enjoyed the paper and thanks for taking the time to consider its implications. I'm happy to answer your questions. 1) For clarity, the...
6090
Ken
kenstanley01
May 8, 2013 1:07 am
Hi Martin, I think the challenge with looking at just the substrate is deciding how to determine what is novel just on the basis of the substrate. Technically...
6089
martin_pyka
May 7, 2013 2:26 pm
Hi Sebastian thanks for the link. But I am more interested in measuring evolvability in the substrate itself rather than the behaviour that is generated by a...
6088
Sebastian Risi
sebastian.risi
May 7, 2013 1:42 pm
Hi Martin, We actually compared the evolvability of HyperNEAT to Evolvable-Substrate HyperNEAT (ES-HyperNEAT) in our recent Artificial Life paper: Sebastian...
6087
martin_pyka
May 7, 2013 12:44 pm
Hi, inspired by the evolvability-article by Joel and Ken I was wondering how one would measure the degree of evolvability of an HyperNEAT encoding. I I would...
6086
Ken
kenstanley01
May 7, 2013 3:43 am
Hi All, Thomas and Shimon were gracious enough to share with me this paper early on, so I have had time to consider its implications. Both Thomas and Shimon...
6085
Thomas van den Berg
tgvdberg
May 6, 2013 4:01 pm
Dear Colleagues, The paper "Critical Factors in the Performance of HyperNEAT", written by Shimon Whiteson and me, was accepted for GECCO2013. It is based on...
6084
Jeff Clune
jeffreyclune
May 3, 2013 7:04 pm
Hello Joel and Ken, Congrats on the excellent paper. I enjoyed it. Congrats also on the nice press coverage. My weekly KurzweilAI.net email this week has your...
6083
Jean-Baptiste Mouret
mandor_42
May 2, 2013 10:15 am
**Please forward this email to anyone who might be interested** The Evolutionary Robotics group in ISIR (UPMC, Paris, France) is seeking a post-doc fellow who...
6082
martin_pyka
Apr 29, 2013 9:50 pm
here are my two cents on this paper (I hope I correctly understood the paper and Colins explanations) . the idea to search for solutions with maximal entropy...
6081
Jeff Clune
jeffreyclune
Apr 29, 2013 5:12 pm
Thanks for the ideas Colin. It seems you are trying to come up with your own new algorithm for how you could maximize entropy of future states. It is telling...
6080
Colin Green
alienseedpod
Apr 27, 2013 7:37 am
... The other way of looking at this is as follows. Think about a typical entropic force such as diffusion of a gas in a tube (see the diagram on the wiki page...
6079
joel278
Apr 27, 2013 1:09 am
Interestingly, the article has made the front page of some popular science blogs -- namely, Science Daily...
6078
joel278
Apr 27, 2013 1:04 am
Hi Martin, Your illustration (http://www.martinpyka.de/wp-content/uploads/2013/04/evolvability.png) is very helpful in teasing apart how undirected genetic...
6077
joel278
Apr 26, 2013 7:27 pm
The idea also seems very related to Nehaniv's concept of 'empowerment', where an agent tries to maximize its mobility and future options; there are results in...
6076
Amy K. Hoover
akhoovr
Apr 26, 2013 3:42 pm
Evolutionary Art, Design, and Creativity Competition to be held as part of the 2013 Genetic and Evolutionary Computation Conference (GECCO-2013) July 6-10,...
6075
martin_pyka
Apr 26, 2013 10:25 am
Hi Joel, thanks for your fast response which addressed exactly my inquiry. First, I want to clarify that even if evolvability can reach a maximum the...
6074
joel278
Apr 26, 2013 3:55 am
Hi Martin, Thanks for the kind words about the paper and for incorporating it into a lecture already! I am happy to try and answer your question, which relates...
6073
Colin Green
alienseedpod
Apr 25, 2013 10:52 pm
... I figure you can get an approximate measure using a number of monte carlo simulations. If there are small variations in initial state (x) for each run then...
6072
martin_pyka
Apr 25, 2013 10:24 pm
Hi Joel, Congratulations to this paper. I read it already, when you put it on arxiv, but great to see that it is now published as a reviewed paper. I think you...
6071
Jeff Clune
jeffreyclune
Apr 25, 2013 6:12 pm
Hello all, Can anyone explain this technique in a language we all can understand? I was actually interviewed for that InsideScience story, and as you can see...
6070
joel278
Apr 25, 2013 3:17 am
Ken Stanley and I are pleased to annouce our new article, "Evolvability is Inevitable: Increasing Evolvability without the Pressure to Adapt," which was...
6069
Ken
kenstanley01
Apr 25, 2013 3:16 am
Hi Greg, thanks to both you and Colin (in his prior post) for pointing out his work. As a non-objective type of behavioral search, it is indeed reminiscent of...
6068
Sebastian Risi
sebastian.risi
Apr 23, 2013 11:46 pm
(apologies for multiple posting.) Dear colleagues, We invite contributions to our AAAI 2013 Fall Symposium titled “How Should Intelligence be Abstracted in...
6067
Jean-Baptiste Mouret
mandor_42
Apr 23, 2013 4:05 pm
Hi all, ... I would like this kind of system very much. Actually, it not that far from a more classic system in which conferences have a very high acceptance...
6066
Greg
greg_barton
Apr 22, 2013 4:24 pm
http://www.insidescience.org/content/physicist-proposes-new-way-think-about-intelligence/987 From the article: 'Entropica's intelligent behavior emerges from...
6065
Nicolas Bredeche
nekonaute
Apr 22, 2013 12:54 pm
Hi all, It's really great we can have this conversation here. While I agree that papers with few results and very good ideas should be published occasionally,...
Hi, Thanks Ken for going on arguing on this very interesting and important question. I don't agree with you relative to quantification. For me, all your ...
