[mlpack] gsoc 2019

[Marcus Edel]

Hello,

thanks for reaching out, the main focus of the project is to implement a stable
and fast version of NEAT, that works with Arbitrary functions, see
https://www.ensmallen.org/docs.html#function-type-documentation for more
information (all we need is a function that implements the Evaluate method). For
testing, you could select from
https://github.com/mlpack/ensmallen/tree/master/include/ensmallen_bits/problems
or implement your own function e.g. another example might be to test it on a
game like Mario, see https://github.com/zoq/gym_tcp_api for more information.

I hope anything I said was helpful, let me know if I should clarify anything.

Thanks,
Marcus

> On 1. Mar 2019, at 20:46, ButtWait! <sohailk1999 at gmail.com> wrote:
> 
> It’s regarding NEAT project
> I do not understand what exactly are we suppose to code. I mean it says we need to work the algorithm on different test functions but what exactly are the test function.
> I be happy if you can give me an example regarding it. 
> Are we suppose to develop an general code which will apply neural evolution on any thing??
>  
> _______________________________________________
> mlpack mailing list
> mlpack at lists.mlpack.org <mailto:mlpack at lists.mlpack.org>
> http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack <http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20190301/546c1a19/attachment.html>