[mlpack-git] [mlpack/mlpack] NeuralEvolution - implemented gene, genome (#686)

[Marcus Edel]

> +  LinkGene link3(2, 3, 0, 0);
> +  LinkGene link4(0, 4, 0, 0);
> +  LinkGene link5(1, 4, 0, 0);
> +  LinkGene link6(2, 4, 0, 0);
> +  LinkGene link7(4, 3, 0, 0);
> +
> +  linkGenes.push_back(link1);
> +  linkGenes.push_back(link2);
> +  linkGenes.push_back(link3);
> +  linkGenes.push_back(link4);
> +  linkGenes.push_back(link5);
> +  linkGenes.push_back(link6);
> +  linkGenes.push_back(link7);
> +
> +  Genome seedGenome = Genome(0, neuronGenes, linkGenes, numInput, numOutput, depth, fitness);
> +

I think it would be a good idea to set a default initial genome inside the CNE method. The authors start with a genome where each input unit is connected with the output units. But, we could also use a hidden units as you did. This way, we can directly start by evolving the network.

---
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/686/files/65f093daf32f6cb353cd6b9304bab88a5e096fdc#r66709850
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160611/4c07ffbc/attachment.html>