Re: [boost] [gsoc 2008] Neural Networks library

From: Arash Partow (arash_at_[hidden])
Date: 2008-03-24 17:21:39

Hi Milan,

Your proposal sounds like a "nice" idea, but wouldn't it be better to generalize
your ANN library into a generic maximum likelihood estimation library - because
at the end of the day that is what an ANN is, nothing more nothing less it would
also provide the users of the library access to other estimation/modeling paradigms,
which is a good thing.

Arash Partow
__________________________________________________
Be one who knows what they don't know,
Instead of being one who knows not what they don't know,
Thinking they know everything about all things.
http://www.partow.net

Milan Rusev wrote:
> Hello,
> 
> I'm an AI student and I'd like to participate in this year's SoC with an
> Artificial Neural Networks library.
> The library will consist of basic elements of a NN: neurons, layers,
> teaching algorithms,
> neuron functions (plus common usages: linear, sigmoid, gaussian,
> winner-takes-all).
> It will also include the implementation of some popular NNs: Multilayer
> Perceptron, Hopfield Network, Kohonen Network.
> I know it's a bit of a high level library, and I'd like some feedback
> whether it's appropriate for Boost.
> 
> I also have a question. The proposal on the GSoC 2008 page for the
> implementation of Fixed Decimal also sounds appealing to me.
> So should I choose one project and apply for it or should I apply for both
> of them separately?
> 
> Milan