neat at Yahoo! Groups

Re: HyperNEAT Tutorial?

Ken — Mon, 09 Nov 2009 21:09:28 GMT

Yes I would advise starting out with NEAT to get familiar with it. However, we can also look into improving the understandability of the HyperNEAT C++

Re: Odd speciation behaviour

rvonwahlde — Mon, 09 Nov 2009 20:15:30 GMT

Buckland's NEAT for windows code uses the Adjusted Fitness to calculate Span Amount. Is this incorrect? In CSpecies::AdjustFitnesses(), for each member of a

Re: Odd speciation behaviour

rvonwahlde — Mon, 09 Nov 2009 19:44:15 GMT

Buckland's NEAT for windows code uses the Adjusted Fitness to calculate Span Amount. Is this incorrect? In CSpecies::AdjustFitnesses(), for each member of a

Re: announcing new mailing list on Evolutionary Design of Robots

Ken Lloyd — Mon, 09 Nov 2009 12:02:35 GMT

Nicholas, Thanks for the notice. Likewise, be aware of HART (Human, Agent, Robot, Teamwork). There is substantial research and application of evolutionary,

announcing new mailing list on Evolutionary Design of Robots

Nicolas Bredeche — Mon, 09 Nov 2009 08:25:48 GMT

Dear all, Following the IROS workshop on Evolutionary Design of Robots held in october 2009, during IROS, we are starting a new mailing list regarding general

Re: HyperNEAT Tutorial?

ramses_vi — Mon, 09 Nov 2009 04:41:35 GMT

Andrei, if you want to learn the underlying NEAT method by looking at c++ code, the best I have seen is Dr. Kenneth Stanley's rtNEAT c++ code. It is fairly

Re: HyperNEAT Tutorial?

Andrei Rusu — Sat, 07 Nov 2009 15:09:45 GMT

I should have specified that I was talking exclusively about the HyperNEAT 2.6 C++ implementation. I read some of the publications and the ideas are

Re: HyperNEAT Tutorial?

Ken — Sat, 07 Nov 2009 14:49:12 GMT

Andrei, which version of HyperNEAT are you interested in and what references have you looked at so far? We can potentially improve the documentation based on

HyperNEAT Tutorial?

Andrei — Sat, 07 Nov 2009 13:52:42 GMT

Can anyone please recommend some HyperNEAT documentation, a tutorial, diagram, some clue, or anything that does not mean reverse engineering the comment-less

Re: CPPNs. Recursive vs Feedforward

Colin Green — Wed, 04 Nov 2009 08:46:52 GMT

2009/11/4 jgmath2000 ... Noted. Thanks.

Re: CPPNs. Recursive vs Feedforward

jgmath2000 — Wed, 04 Nov 2009 05:24:29 GMT

Hey Colin, CPPNs, being an indirect encoding, allow for small changes in the genotype to have profound effects on the resulting substrate. While this is what

Re: CPPNs. Recursive vs Feedforward

Jean-Baptiste Mouret / Mandor — Tue, 03 Nov 2009 23:23:28 GMT

Hi Colin, ... Yes, this is exactly the second approach listed in the DAG part (i.e. "Using shortest-path algorithms") since a feed-forward NN is obviously a

Re: CPPNs. Recursive vs Feedforward

Colin Green — Tue, 03 Nov 2009 23:19:16 GMT

2009/11/3 Ken ... [...] Thanks. From reading your response my instinct is to use feedforward as the default/baseline for CPPNs and to

Re: CPPNs. Recursive vs Feedforward

Colin Green — Tue, 03 Nov 2009 23:07:36 GMT

2009/11/3 Jean-Baptiste Mouret / Mandor ... Thanks. I wonder if this is the same approach for DAGs listed here:

Re: CPPNs. Recursive vs Feedforward (Efficient Feedforward)

Colin Green — Tue, 03 Nov 2009 22:41:38 GMT

2009/11/3 Ken ... [...] ... Yes I see. It's like evaluating an expression tree but with an extra rule for handling the fact it's not a