+1 on doing these things. I'm not sure if the work that needs to be done is ideal for GSoC, though. I can't really judge that. Merging the RBM is very high on my priority list, and so is getting the MLP done. I can't mentor, though.
On 03/22/2013 10:46 AM, Vlad Niculae wrote: > 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 ------------------------------------------------------------------------------ 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
