Hello, I am just experimenting with implementation of neural network based on http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial made by the team of Andrew Ng on Stanford. I am thinking about creating the library covering this functionality in Python (object-oriented with NumPy). Covering the code with tests and creating documentation. I have some experience with http://eigen.tuxfamily.org/, so I will eventually rewrite this library (or its parts) in C++ and create bindings in the future.
Do you thing it will be useful to add this functionality to scikit-learn sometime in the future? There is http://sklearn-theano.github.io/feature_extraction/index.html with similar purpose, but I found UFLDL more basic and straightforward. It also corresponds quite well with NN described in http://www-bcf.usc.edu/~gareth/ISL/ , which I found nice. Best regards, Jiří Fejfar. ------------------------------------------------------------------------------ One dashboard for servers and applications across Physical-Virtual-Cloud Widest out-of-the-box monitoring support with 50+ applications Performance metrics, stats and reports that give you Actionable Insights Deep dive visibility with transaction tracing using APM Insight. http://ad.doubleclick.net/ddm/clk/290420510;117567292;y _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
