http://groups.yahoo.com/group/neat/ NEAT Users Group Tue, 18 Jun 2013 19:52:51 GMT Sebastian Risi http://groups.yahoo.com/group/neat/message/6155 http://groups.yahoo.com/group/neat/message/6155 (apologies for multiple posting.) Dear Colleagues, This is just a reminder that the submission deadline for our AAAI 2013 Fall Symposium on "How Should Tue, 18 Jun 2013 03:01:23 GMT Ken http://groups.yahoo.com/group/neat/message/6154 http://groups.yahoo.com/group/neat/message/6154 Hi Shimon, The nice thing about this type of conversation is that it pushes us towards realizing our fundamental assumptions. In that spirit, a few other Mon, 17 Jun 2013 15:19:11 GMT Vassilis Vassiliades http://groups.yahoo.com/group/neat/message/6153 http://groups.yahoo.com/group/neat/message/6153 Hi Shimon, I have some questions regarding what you said about using bandit algorithms to design NN/CPPN topologies. Do you believe that in order to tackle Mon, 17 Jun 2013 14:30:04 GMT Drew Kirkpatrick http://groups.yahoo.com/group/neat/message/6152 http://groups.yahoo.com/group/neat/message/6152 Stephane, As promising as NCD is, I think the only realistic approach to speeding it up is to use faster and faster compression algorithms (or more hardware). Mon, 17 Jun 2013 13:58:37 GMT Ken Lloyd http://groups.yahoo.com/group/neat/message/6151 http://groups.yahoo.com/group/neat/message/6151 Shimon, Neural networks are obviously represented by (possibly recurrent) graph networks. The connective dynamics of graph networks, and their distribution, Mon, 17 Jun 2013 11:54:52 GMT shimonw http://groups.yahoo.com/group/neat/message/6150 http://groups.yahoo.com/group/neat/message/6150 Hi Ken, If I may, I'd like to offer a couple reactions to your latest message. This is indeed an interesting discussion that touches on many potentially Sat, 15 Jun 2013 19:32:53 GMT Ken http://groups.yahoo.com/group/neat/message/6149 http://groups.yahoo.com/group/neat/message/6149 Hi Stef, It looks like we just posted at the same time. I think we are in agreement that if only one is to be used, behavioral diversity is the priority. The Sat, 15 Jun 2013 19:27:43 GMT Ken http://groups.yahoo.com/group/neat/message/6148 http://groups.yahoo.com/group/neat/message/6148 Oops I had forgotten that we actually do have experimental results supporting the idea that genetic diversity can be important for maintaining behavioral Sat, 15 Jun 2013 19:27:13 GMT Stéphane Doncieux http://groups.yahoo.com/group/neat/message/6147 http://groups.yahoo.com/group/neat/message/6147 Hi Ken, I certainly did not want to say that genetic diversity is not important. I just wanted to say that behavioral diversity should not be neglected and Sat, 15 Jun 2013 18:38:18 GMT Stéphane Doncieux http://groups.yahoo.com/group/neat/message/6146 http://groups.yahoo.com/group/neat/message/6146 Hi, we have also tried NCD with gzip and it was really too slow. If someone knows how to estimate it in a reasonable time, I am interested... By the way, a Fri, 14 Jun 2013 21:36:39 GMT Ken http://groups.yahoo.com/group/neat/message/6145 http://groups.yahoo.com/group/neat/message/6145 Hi Stef, I changed the subject again just to make it easier to keep track as the conversation branches. Thanks for pointing out these insights and your work on Fri, 14 Jun 2013 18:08:27 GMT Randy Olson http://groups.yahoo.com/group/neat/message/6144 http://groups.yahoo.com/group/neat/message/6144 BEACON put up a blog post for the top entries: http://beacon-center.org/blog/2013/06/14/beacon-evolved-art-competition-results/ Always impressed with the Fri, 14 Jun 2013 15:23:38 GMT Drew Kirkpatrick http://groups.yahoo.com/group/neat/message/6143 http://groups.yahoo.com/group/neat/message/6143 Josh, I tried a number of methods to speed up the speed of NCD in my second M.S. thesis. Some of the approaches I used do deviate from the more general Fri, 14 Jun 2013 15:09:47 GMT Joshua Auerbach http://groups.yahoo.com/group/neat/message/6142 http://groups.yahoo.com/group/neat/message/6142 Drew, (changed the subject, since this is branching off into a separate topic) I actually have played some with NCD (using gzip) but found it to be Fri, 14 Jun 2013 14:35:40 GMT Drew Kirkpatrick http://groups.yahoo.com/group/neat/message/6141 http://groups.yahoo.com/group/neat/message/6141 Josh, As far as behavioral diversity goes, there's been some interesting papers on using information distance. I used a normalized compression distance (really