Ken, I was thinking along the lines of a wiki that would initially be set up to contain a tutorial/hands-on with one or two examples. The community could then,...
Hi Daniel, Thanks for your interest in HyperSharpNEAT. It's always good to hear about new researchers working with it, and it's great that you found this...
Evert, the wiki idea is interesting. How do you see that working? Would it be a place for the general public to post advice and information? I am talking to...
Hello Colin, yes, the network had a few thousand connections. The network was not intended to produce any meaningful output, I have just played around to see...
Hello, I've played around with a quite large network and took a look at the execution performance of HyperSharpNEAT. There was one outstanding method (besides...
Hello, This email message is a notification to let you know that a file has been uploaded to the Files area of the neat group. File :...
neat@yahoogroups.com
Nov 24, 2009 1:31 am
4915
Hey Ken, thanks for all the information. I guess I was partly looking for some idea of what attempts people had made at parallelizing NEAT and sounds like...
Jeff, You have raised many points that are quite interesting. The problem: There are too many opportunities, and too little time. My work deals with massively...
Hello Ken, here's just another vote for a tutorial, with the difference that I would prefer it for HyperSharpNEAT. It would be great to see something like a...
Of course, thanks for the clarification. I felt something was off but I wasn't sure what it was :) Cheers, Jeff ... -- ...imagine a puddle waking up one...
Jeff, makes sense, thanks for the clarification. By the way, I think there is a little confusion with people's names: There are two different "Kens" who have...
Ah, no, sorry, just meant that I thought NEAT was the best approach to neuroevolution to date. I don't have any good reason to suspect that F# is particularly...
Mark, have you tried running a simpler experiment in which you simply train an agent to collect food scattered over a 2-D world? That might be a good sanity...
Jeff, I'm not familiar enough with F# to judge whether it is well-suited for NEAT or not. However, I was curious what you meant when you said, "Always thought...
Different versions of NEAT will vary in precisely how they allocate offspring to species. However, ideally the number of children assigned to each species...
Sorry for the off-topic message: A user from this group "dkuppitz" emailed me, but the my response was blocked with the following reason: This account has been...
2009/11/20 rvonwahlde <rvonwahlde@...> ... species spawns is greater than the desired ... Hi, I'd strongly recommend taking a look at the sharpneat 2...
How do you work around the problem when the total number of children each species spawns is greater than the desired population size? Buckland's NEAT for...
Hey Ken, thanks for the note. Yeah, I agree that the parallel extensions are a good alternative. I am definitely not more comfortable in declarative ...
Hi Jeff, F# tends to be declarative, which is fine if that paradigm is more comfortable for you. There are .NET Extensions for Parallel Processing if you...
Hi, I've been quiet on this group for a long time although I've kept my subscription so I remember to play with NEAT once I have free time (presumably...
It is normalized. In full, I'm testing to find the nearest object, then using (200-d)/200. Since d will range from very small numbers to 200, that gives me a...
Mark, there is one detail in your setup that sounds potentially very problematic, although it is possible I am misunderstanding. You say that the sensor is...
The food foraging experiment is the dangerous food foraging example from "Evolving Adaptive Neural Networks with and without Adaptive Synapses". The sensors...
Hi Mark, I'm only a newbie, but I've hit similar issues when running some experiments. In my case, the it was a multi-threading issue. It highlighted to me...
Mark, which food foraging experiment are you implementing? That is, from which paper? What are the sensors and outputs for your neural networks? I may be...
I've been trying on and off the last couple months to get a couple control experiments running, and have been getting results that appear to have almost a...
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.
