Print

Print


On Nov 21, 2011 11:15 AM, "Ben Stabile" <[log in to unmask]> wrote:

>   I'm actually interested in the "hybrid" notion that Frederik was asking
> about (as opposed to the co-evolutionary solution suggested by Sean).
>
> My work involves neural networks that have both qualitative and
> quantitative characteristics. That is, they have topological structure that
> can be evolved with the traditional GP Tree-based approach. However, the
> high-dimensional weighted connectivity between nodes, and parameterized
> transforms within the nodes, can be efficiently optimized using other
> traditional ANN techniques.  The way I’ve been dealing with this in the
> past, is to evolve networks using GP to “explore” the structural solution
> space, and then rely on training (evaluation) to exploit the available
> solution sub-space which can be done using GA, gradient descent, and so on.
> This is obviously computationally expensive, no matter how you dice it.
>
> I wonder if an implementation of HyperNEAT<http://eplex.cs.ucf.edu/hyperNEATpage/HyperNEAT.html>
> evolution could be added to ECJ that would efficiently blend these things
> in an elegant way? Has anyone out there tried this?
>
> The robotics sensor issues Frederik mentioned, despite my lack of
> knowledge in that problem domain, sound very familiar to me.
>
> Regards,
>
> Ben Stabile
>
>
> -----Original Message-----
> From: Frederik
> Sent: Monday, November 14, 2011 11:49 AM
> To: [log in to unmask]
> Subject: A Mixed GA/GP individual
>
> Dear all,
>
> I've been experimenting with ECJ for some weeks now. I have a fellow
> student's
> code who already succeeded to do develop robot controllers using GP
> individuals
> and an extern simulator.
>
> What I want to try now is to evolve some kind of indivual where the
> controller still
> is a GP individual (subpopulation 0?) but the senors are coded into a
> vector of bits
> or integers (subpopulation 1?) . Breeding should be between vectors or
> controllers
> of the same individuals. Is there an easy way to do such a thing? Is there
> a
> similar predifined parameter file for this?
>
>
> Thank you in advance,
> With kind regards,
> Frederik
>