Hello Marcus, Thank you for your reply!
That sounds interesting, can you tell us more about the project you worked > on? There is a planetarium program called KStars that is a part of KDE Education package. This program allows you see the map of the night sky, explore different space objects, control your telescope and a lot of other amateur astronomy-related stuff. My task was to make an Android version called KStars Lite that would share the same codebase (though I migrated the whole graphics part to the new graphical backend, the data part is still the same). You can check my work on this page (nickname: polaris) https://summerofcode.withgoogle.com/archive/2016/projects/5053062041305088/ and try it yourself on your Android device https://play.google.com/store/apps/details?id=org.kde.kstars.lite. I was working with Qt framework that is based on C++ so I have some C++ background. There is definitely room to extend/improve the existing collaborative > filtering > framework, there might even be the option to combine deep learning with > collaborative filtering: https://github.com/robi56/Deep-Learning-for- > Recommendation-Systems That sounds very interesting! I will definitely look at the papers and read the ones I like. We are trying to add new entrance issues over the next days, That would be very nice, thank you very much. Regards, Artem On Mon, Feb 5, 2018 at 7:48 PM, Marcus Edel <[email protected]> wrote: > Hello Artem, > > thanks for getting in touch. > > My name is Artem Fedoskin. I have already written to this mailing list but > I > think it would be good to introduce myself. I study a Master's Degree in > Data > Analytics at University of Hildesheim (Germany). I have already > participated in > GSoC 2016 in KDE with the project that involved C++ and Qt framework > (KStars > Lite). > > > That sounds interesting, can you tell us more about the project you worked > on? > > Is it possible that more than one student will work on Deep Learning > Modules? We > could implement different algorithms. > > > Yes, that's possible, note that the models on the ideas page are just > suggestions, if you like to implement another interesting model please > feel free > to start a discussion. > > Apart from Deep Learning I'm very interested in collaborative filtering. > Our > lectures have already covered some of the main concepts and I'm very > interested > in that area. > > > There is definitely room to extend/improve the existing collaborative > filtering > framework, there might even be the option to combine deep learning with > collaborative filtering: https://github.com/robi56/Deep-Learning-for- > Recommendation-Systems > > I have compiled mlpack and tried several examples. I'm currently looking > at what > I could do on GitHub but I would be very grateful if you could point me to > some > issue related to the projects I'm interested in. > > > We are trying to add new entrance issues over the next days, in the > meantime, > you can always glance over the codebase and perhaps think about ways to > improve > or extend a specific method. > > I hope some I said was helpful, let us know if we should clarify anything. > > Thanks, > Marcus > > On 5. Feb 2018, at 02:41, Artem Fedoskin <[email protected]> wrote: > > Dear developers of mlpack, > > My name is Artem Fedoskin. I have already written to this mailing list but > I think it would be good to introduce myself. I study a Master's Degree in > Data Analytics at University of Hildesheim (Germany). I have already > participated in GSoC 2016 in KDE with the project that involved C++ and Qt > framework (KStars Lite). > > Indeed I'm very interested in Machine Learning and I was very happy to > find your library. Though now I primarily use Python for Data Science > purposes, I would be very happy to use my C++ knowledge for Machine > Learning. > > I'm particularly interested in following projects: > 1. Essential Deep Learning Modules > 2. Alternatives to neighborhood-based collaborative filtering > 3. Reinforcement Learning > > Is it possible that more than one student will work on Deep Learning > Modules? We could implement different algorithms. > > Apart from Deep Learning I'm very interested in collaborative filtering. > Our lectures have already covered some of the main concepts and I'm very > interested in that area. > > I have compiled mlpack and tried several examples. I'm currently looking > at what I could do on GitHub but I would be very grateful if you could > point me to some issue related to the projects I'm interested in. > > Regards, Artem Fedoskin > _______________________________________________ > mlpack mailing list > [email protected] > http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack > > >
_______________________________________________ mlpack mailing list [email protected] http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
