Hi Vijay,
> I am Vijay Mahantesh SM from India. I am an open
> source enthusiast and a big fan of computational mathematics and research.
> I came across the idea list of mentioned in the
link<http://trac.xapian.org/wiki/GSoCProjectIdeas> and
> was fascinated to find projects of my passion. As per my understanding of
> the project, this project requires a good exposure of C++ along with
> knowledge of certain subjects ML. I have an adept hands on experience in
> C++ and i have done a Stanford online course on Machine Learning and i am
> quite familiar with Support Vector Machine, Learning scheme such
> as Bayesian Methods, Clustering Kmeans Algorithm etc.
>
> I had previously worked on research project in Complex
> Networks "A Navigation Algorithm Inspired by Human
Navigation<http://arxiv.org/abs/1111.4898>",
> "Prediction Of Arrival Of Nodes In A Scale Free
Network<http://arxiv.org/abs/1111.4886>".
> I have a gained a good knowledge in Machine Learning with the help of my
> first paper on " A Navigation Algorithm inspired by human
navigation".
>
Thanks for the information. Your experience in ML can help you in
understanding the Learning to rank.
>
> What are the new algorithms planed to be implemented in
> Letor ? I think Letor doesn't have a support for decision graphs,
> naive-bayes, decision tables. I have these algorithms in mind to work as
> a GSOc project. Is it feasible and is my understanding of the problem
> correct ? I want to know more about the project.
>
I have just updated the idea page with some existing algorithms. You can
choose any according to your interest (not necessarily) from the list. I
would suggest to choose one algorithm soon and have basic understanding of
it and simultaneously start getting familiar with the existing letor
infrastructure. That will help you in drafting your application.
Regards,
Parth.
>
> Looking forward to hear from you.
>
> Regards,
> Vijay Mahantesh SM
> 6th Sem,
> PESIT,
> Bangalore,
> India.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.xapian.org/pipermail/xapian-devel/attachments/20120330/89b94347/attachment.htm>
