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 2635 - 2664 of 4886   Oldest  |  < Older  |  Newer >  |  Newest
Messages: Simplify | Expand   (Group by Topic) Author Sort by Date ^
2635
Hi, I've uploaded a zip file of my first results to the SLEAT folder in the file area. It is "TTT 1 Analysis.zip" and all you need to do is unzip it into a...
Ian Badcoe
ian_badcoe
Offline Send Email
May 16, 2006
7:56 pm
2636
Hi Ian, looks like you did a pretty comprehensive analysis. I don't know what all the variables mean so I'll wait for you explanation, but one thing I noticed...
Kenneth Stanley
kenstanley01
Offline Send Email
May 17, 2006
9:59 pm
2637
Hi, OK so I finally have to results to ponder. Let me tell you what I think in no particular order... ...and ask everyone for anything they can think of to...
Ian Badcoe
ian_badcoe
Offline Send Email
May 17, 2006
10:21 pm
2638
Ian, it sounds like some results are inconclusive, but that may not be a bad things because it may imply that the algorithm is somewhat robust to parameter...
Kenneth Stanley
kenstanley01
Offline Send Email
May 22, 2006
3:07 am
2639
... This is true. I'm now going to vary the ones that do have an effect a bit further, to try and find a rough optimum. Just to improve the speed of further ...
Ian Badcoe
ian_badcoe
Offline Send Email
May 22, 2006
11:32 am
2640
... I may have to dig around in the archives and see if there's a more detailed explanation of this technique (did you post one before?). This certainly seems...
Derek James
blue5432
Offline Send Email
May 22, 2006
1:15 pm
2641
... Yup, look for something with "TTT PPS" in the title, I think. I think I even posted example code at one point... ... I don't care how far away in the...
Ian Badcoe
ian_badcoe
Offline Send Email
May 22, 2006
3:34 pm
2642
Hi all I am a second year student at the Indian Institute of Technology, Kanpur, and am currently working under a summer undergraduate research program. My...
sidhantdash
Offline Send Email
Jun 3, 2006
2:07 pm
2643
Sidhant, If I understand your question correctly, you're asking if structural mutations should be compared to previous generations' innovation numbers, as well...
Brian Allen
dexter_allen
Offline Send Email
Jun 3, 2006
6:55 pm
2644
... Yeah, I'm not quite sure what you mean here. Could you elaborate please? --Derek...
Derek James
blue5432
Offline Send Email
Jun 4, 2006
9:52 pm
2645
... is that ... only in ... please? ... I could be wrong but I'm guessing like Brian that the question is about how long to keep around the list of...
Kenneth Stanley
kenstanley01
Offline Send Email
Jun 4, 2006
10:26 pm
2646
We've just released Metavolv, which can search for good parameters for YOUR program. The attach HTML file, and diagram, is the documentation. Metavolv is open...
Mitchell Timin
zenguyuno
Offline Send Email
Jun 10, 2006
4:17 am
2647
The attached text file describes the problem. As you might guess, I've been working on it. I have had moderate success. My best ANNs can produce 90% of the...
Mitchell Timin
zenguyuno
Offline Send Email
Jul 1, 2006
1:31 am
2648
... This sounds like an interesting task and a useful area to explore. It makes sense that as the "path" gets longer the ANN performs less and less well. I'm...
Derek James
blue5432
Offline Send Email
Jul 1, 2006
2:37 pm
2649
... You are cetainly correct that in the biological case, a one-bit error ruins the return path, since it no longer takes the animal home. And also, as you...
Mitchell Timin
zenguyuno
Offline Send Email
Jul 1, 2006
4:46 pm
2650
Hello All, I stumbled onto NEAT a short time ago, and I think its an amazing piece of work - I'm not an expert on ANN's / Genetic Algorithms by any means, but...
rognorak
Offline Send Email
Jul 3, 2006
6:55 pm
2651
Hi Mitchell, All, I've intended to look into tasks requiring memory for some time now, and it should be really easy to throw together soem code for SharpNEAT...
Colin Green
alienseedpod
Offline Send Email
Jul 3, 2006
11:17 pm
2652
... I'd recommend one of Ken's early publications where he first lays out the algorithm, like this one: ...
Derek James
blue5432
Offline Send Email
Jul 3, 2006
11:18 pm
2653
Hi Mike, ... Currently there is no setting to do this so you would have to modify the code. One way would be to add the fitness threshold as a property on ...
Colin Green
alienseedpod
Offline Send Email
Jul 3, 2006
11:23 pm
2654
... No, I started out with this one. But it's prolly a good idea to try the simpler one first. I'm not sure why I skipped that step. In my latest version I...
Mitchell Timin
zenguyuno
Offline Send Email
Jul 3, 2006
11:56 pm
2655
... by ... always ... might ... seem ... NEAT ... out the ... (Pubs)=114 ... To expand on to Derek's suggestion- although our papers on NEAT do tend to focus...
Kenneth Stanley
kenstanley01
Offline Send Email
Jul 4, 2006
10:46 am
2656
First Off, thanks to everyone who replied to my questions, its good to see a newbie-friendly discussion group :) I have a lot of reading to do. In response to...
rognorak
Offline Send Email
Jul 7, 2006
3:22 pm
2657
Hey everyone, I wanted to post a quick message about what I've been up to recently. As some of you know, I started as an assistant professor at UCF 6 months...
Kenneth Stanley
kenstanley01
Offline Send Email
Jul 8, 2006
6:45 pm
2658
... good ... reading ... network, ... training? ... is ... to ... Mike, you can do that with NEAT alone. What you do is evaluate each generation on the...
Kenneth Stanley
kenstanley01
Offline Send Email
Jul 8, 2006
7:11 pm
2659
All, Just in case anyone might be interested, I have a paper on some of my work for a hardware accelerator for NEAT. It's available at the following url: ...
Daniel Larkin
daniel.larkin
Offline Send Email
Jul 12, 2006
4:33 pm
2660
All, For those that remember, I originally got interested in NEAT in order to do image enlargement. The primary thing that has stood in the way of progress, ...
John Arrowwood
jarrowwx
Offline Send Email
Jul 12, 2006
7:41 pm
2661
I just found out that the version that was up of my tech report on CPPNs had been checked by a buggy spellchecker that let through a lot of typos. I never...
Kenneth Stanley
kenstanley01
Offline Send Email
Jul 13, 2006
2:19 am
2662
I cannot see any files in the CVS folder on SourceForge for SharpNEAT. I know that the source is included in the package for SharpNEAT 1.04 but is there also...
petervermont
Offline Send Email
Jul 13, 2006
4:33 pm
2663
I have noticed that my best fitness sometimes declines. While I can sort of understand this if I have enabled 'pruning', it also occurs even when I disable...
petervermont
Offline Send Email
Jul 13, 2006
4:57 pm
2664
... Ok two points to start with: 1) SharpNEAT will always preserve the species with the best genome, even if it has reached the drop-off age. 2) Pruning isn't...
Colin Green
alienseedpod
Offline Send Email
Jul 13, 2006
10:02 pm
Messages 2635 - 2664 of 4886   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