Hi Abinash, Indeed, like Andy said, you should first get familiar with the codebase by starting to contribute on easy issues, even if they are not related to what you want to work on.
Second, regarding the multi-layer perceptron: there are two codebases under development implementing it. One of them was started by David Marek during last year's GSoC under the supervision of Andy, but David abandoned the project after getting a better offer. The effort was picked up by Hannes here: https://github.com/scikit-learn/scikit-learn/pull/1653 The second one was started from scratch by Lars here: https://github.com/scikit-learn/scikit-learn/pull/1395 and it seems to have a better design, but everything is up for discussion at this point (see the comments here https://github.com/scikit-learn/scikit-learn/pull/1653#issuecomment-13076352) Even if much of the work has been done, it is far from ready, and in my opinion there would be place for a GSoC project with the objectives of (in order) - getting the Restricted Boltzmann Machine ready to merge - getting the MLP ready to merge (https://github.com/scikit-learn/scikit-learn/pull/1200) - implementing an autoencoder (ideally using the same underlying code) - Showing, with an example, how to put them together: using the autoencoder or the RBM to pretrain the weights, then running backprop with the MLP for discriminative training. What does everybody think, especially Andy and Lars? Cheers, Vlad On Fri, Mar 22, 2013 at 8:27 AM, Andreas Mueller <amuel...@ais.uni-bonn.de> wrote: > Hi Abinash. > As you went through the idea page, hopefully you also read Gael's letter. > As stated there, you are expected to contribute to the project prior to > applying for a GSoC. > > Please go through the issue tracker for possible starting points. > If you are undecided, we can try to pick something out for you. > > Cheers, > Andy > > > > On 03/22/2013 06:21 AM, abinash.panda.ece10 wrote: > > Hi I want to participate in GSoc 2013. I went through the idea page and I am > quite interested in Multilayer Perceptron and Neural Network idea. Requiring > help from mentors for getting started. > I thank in advance. > > > Best Regards, > > Abinash Panda > ----------------------- > B.Tech Part -III (2014) > Electronics Engineering > Indian Institute of Technology (BHU), Varanasi > +91-7408853478 > skype id : panda.abinash > > > ------------------------------------------------------------------------------ > Everyone hates slow websites. So do we. > Make your web apps faster with AppDynamics > Download AppDynamics Lite for free today: > http://p.sf.net/sfu/appdyn_d2d_mar > > > > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > > > > ------------------------------------------------------------------------------ > Everyone hates slow websites. So do we. > Make your web apps faster with AppDynamics > Download AppDynamics Lite for free today: > http://p.sf.net/sfu/appdyn_d2d_mar > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > ------------------------------------------------------------------------------ Everyone hates slow websites. So do we. Make your web apps faster with AppDynamics Download AppDynamics Lite for free today: http://p.sf.net/sfu/appdyn_d2d_mar _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
