[boost] [gsoc 2008] Neural Networks library

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