Search the web
Sign In
New User? Sign Up
neat · NEAT Users Group
? Already a member? Sign in to Yahoo!

Yahoo! Groups Tips

Did you know...
Show off your group to the world. Share a photo of your group with us.

Best of Y! Groups

   Check them out and nominate your group.
Having problems with message search? Fill out this form to ensure your group is one of the first to be migrated to the new message search system.

Messages

  Messages Help
Advanced
Messages 3801 - 3830 of 4894   Oldest  |  < Older  |  Newer >  |  Newest
Messages: Simplify | Expand   (Group by Topic) Author Sort by Date ^
3801
Yes Ken. That's also what my question was referring, what advantage does it have. I can see AGE producing complex patterns via a intricate interaction map (or...
JT
skybro77
Offline Send Email
Feb 1, 2008
9:03 am
3802
Hi Kirk, Interesting that so many people are getting into PacMan as a testbed. Understandable maybe, as the game is easy to implement and fast to evaluate. ...
Julian Togelius
jtogel
Offline Send Email
Feb 1, 2008
3:02 pm
3803
Thank you for the links, Julian. I haven't had time to look at them in depth, but they all look very interesting. PacMan has definitely been a topic of...
Robert Kirk DeLisle
newtwist2000
Offline Send Email
Feb 1, 2008
4:33 pm
3804
Yes, you make a good point. If you strip down the whole idea of an "interaction map," all you really have left is a function that takes two nodes as input and...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 1, 2008
11:40 pm
3805
I've just updated the PacMan code again based on some additional feedback. Here's the detail: v0.1.3 Updates ... Windows now update during the evolution step...
newtwist2000
Offline Send Email
Feb 12, 2008
10:09 pm
3806
Hello- I just read the AGE paper, thanks for posting it JT. Ken, I think you raise excellent issues in your analysis of their work. I agree that they do not do...
Jeff Clune
jeffreyclune
Offline Send Email
Feb 19, 2008
4:17 pm
3807
Jeff, I am skeptical that the genetic operators are really that novel compared to any other indirect encoding. Note that the meaning of things like "gene...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 21, 2008
2:17 am
3808
I downloaded the new version and it works a lot better for me. Nice work, I enjoyed playing with it. However, I don't see ghosts. Are there supposed to be...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 23, 2008
8:15 am
3809
Ken, Excellent! I really appreciate your feedback (now and previously) - it has helped me improve the "user experience" of my little PacMan demo. Regarding...
Robert Kirk DeLisle
newtwist2000
Offline Send Email
Feb 23, 2008
11:27 pm
3810
Hi, Does anyone know anything about this: "Stepwise Transition from Direct Encoding to Artificial Ontogeny in Neuroevolution" ...
Colin Green
alienseedpod
Offline Send Email
Feb 24, 2008
12:14 pm
3811
According to google this book/chapter also has references to NEAT in it. Possibly another interesting/relevant read: Part 1: Chapter 1: Evolutionary Visual Art...
Colin Green
alienseedpod
Offline Send Email
Feb 24, 2008
12:40 pm
3812
There doesn't seem to be much on the internet about it, though I did find a link to the guy's email address and sent him a mail asking for a copy of the paper....
Derek James
blue5432
Offline Send Email
Feb 24, 2008
3:55 pm
3813
Hi Colin, I know a lot about the NEON system since I was the external examiner on Benjamin Inden's dissertation (which was on NEON). I am not sure though...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 24, 2008
8:06 pm
3814
That looks potentially interesting. I have a feeling I may have seen a part of that chapter somewhere... maybe it was on the internet as a draft or something?...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 24, 2008
8:11 pm
3815
Since Colin raised the topic of evolutionary art and music, I thought I might point out NEAT Drummer for those who haven't already read about it. We've been...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 24, 2008
8:21 pm
3816
When I graph fitness versus generations, I see large areas where the system is making very little progress. While there can be some small changes in the...
shanemcdonaldryan
shanemcdonal...
Offline Send Email
Feb 25, 2008
10:37 am
3817
Hi, I am the author of the paper of NEON and another one, which may be clearer: Neuroevolution and Complexifying Genetic Architectures for Memory and Control...
benjamin.inden
Offline Send Email
Feb 25, 2008
11:03 am
3818
Dear all, The human brain has different areas that solve different kind of problems. My question is if you think it is a good idea to try encouraging a network...
christofer_fransson
christofer_f...
Offline Send Email
Feb 27, 2008
3:18 pm
3819
I'm trying to reproduce the double pole balancing experiment (following Stanley's code), but something is not clear to me. According to Wieland's equations, we...
Cesar G. Miguel
fdital
Offline Send Email
Feb 28, 2008
4:36 am
3820
Hi Christofer, Given the fact that the nodes have a position in 3D space, it is easy to run a HyperNEAT evolution in a 3D substrate. You can provide a bias...
petar_chervenski
petar_cherve...
Offline Send Email
Feb 28, 2008
7:39 am
3821
Hi Cesar, ... Many double cart-pole (and cart-pole) simulations (including mine neglect this term. I don't know the real reasons but I can suggest some: -...
Jean-Baptiste Mouret ...
mandor_42
Offline Send Email
Feb 28, 2008
9:51 am
3822
I just received an e-mail about a new journal from Springer. I thought this group would be interested. The premier issue appears to have free access to...
newtwist2000
Offline Send Email
Feb 28, 2008
4:03 pm
3823
Please find attached the following weblink: http://www.casde.iitb.ac.in/MDO/specific-studies/Wing-opt-modified-1- 05.ppt to a PowerPoint file containing an MDO...
afcarl2
Offline Send Email
Feb 28, 2008
11:52 pm
3824
Andy, can you elaborate on what you mean by "maintaining a history?" What is it a history of? ken ... 1- ... Optimization) ... MDO ... 92). ... reduced ... ...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 29, 2008
1:08 am
3825
In short, keeping track of where you have already evaluated in the design space, such that a subsequent evaluation request for the same point in the design...
afcarl2
Offline Send Email
Feb 29, 2008
2:25 am
3826
Christofer, I think the modular approach is not always the best or correct approach. In the case of 3-coupled (or more), non-linear, undirected systems, ...
Ken Lloyd
kalloyd2
Offline Send Email
Feb 29, 2008
4:41 pm
3827
Christofer, it's an interesting idea but I think it may be difficult to implement in practice because of the nonlinear relationship among different components...
Kenneth Stanley
kenstanley01
Offline Send Email
Feb 29, 2008
11:22 pm
3828
Another approach is to expand the definition of a node to include more than one unique input and output, and re-introduce a trained genome as a node. And let...
afcarl2
Offline Send Email
Mar 1, 2008
12:49 am
3829
The pole balancing code did not originate with me; I copied it from the prior-existing ESP source code for the experiment. I believe the ESP version may in...
Kenneth Stanley
kenstanley01
Offline Send Email
Mar 1, 2008
8:22 am
3830
Cristofer, Here's an article that describes current research on "real" neural networks, which have bearing on the artificial variety, IMO. Ken ...
Ken Lloyd
kalloyd2
Offline Send Email
Mar 2, 2008
12:06 am
Messages 3801 - 3830 of 4894   Oldest  |  < Older  |  Newer >  |  Newest
Advanced
Add to My Yahoo!      XML What's This?

Copyright © 2009 Yahoo! Inc. All rights reserved.
Privacy Policy - Terms of Service - Guidelines - Help