Thanks Andy, "speeding up" was just an extra suggestion that does not need to be implemented, the main goal is to get the PRs properly integrated as a basis for implementing the DBN, which will be developed as well. Clean documentations and code would surely be the deliverables of this project, thus, GSOC would help scikit get started with deep learning at high momentum :)
Hopefully, there are some mentors for this. I am more of a self-learner developer, thus a mentor would only need to evaluate my progress rather than having to spend his\her time feeding me knowledge :). Best regards, --Issam On 5/4/2013 11:08 AM, Andy Mueller wrote: > Hi Issam. > Please stay on the list ;) > > Sorry I have been so critical of your proposal. > Merging the two PRs is a good proposal. > > I just don't think the "speeding up" is realistic. > As I said, we will not include Numba into scikit-learn very soon. > And we will not include GPU implementations into scikit-learn any time > soon. (I think there is a consensus on this for the time being.) > > For the algorithms: deep believe nets are not really much to program. > They state "train a couple of RBMs, then throw the weights in a neural > network". So implementing a DBN is more about getting the API of RBMs > and MLPs right. > > Sorry, I am a bit behind my mails on scikit-learn and haven't followed > the GSOC process much. > Maybe some of the mentors can say more about the current state? > > Cheers, > Andy > > ------------------------------------------------------------------------------ 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
