Hi Fred, Thanks, I have followed your suggestions and updated my proposal, which can be seen here,
https://google-melange.appspot.com/gsoc/proposal/review/google/gsoc2013/issamou/1# The schedule I devised is an optimistic one, its basically a template of how I would progress. For every implementation of a DL algorithm I would ensure that its highly usable, bug free and efficient, so the schedule could change based on that. If you have some feedback on the updated version, it would be highly appreciated. Thank you! --Issam On 5/2/2013 8:35 PM, Frédéric Bastien wrote: > I just taught that you could consentrate on the DL algo that stack MLP > and RBM as there is a PR for each of them. > > So this would mean helping to finish them. I think it is better to > have fewer but finished model then more model. > > Don't forget my previous disclaimer. > > Fred > ------------------------------------------------------------------------------ Get 100% visibility into Java/.NET code with AppDynamics Lite It's a free troubleshooting tool designed for production Get down to code-level detail for bottlenecks, with <2% overhead. Download for free and get started troubleshooting in minutes. http://p.sf.net/sfu/appdyn_d2d_ap2 _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general