Actually I couldn't find the code but I found something better, the assignment notes:
https://github.com/SaveTheRbtz/ml-class/blob/master/ex4.pdf If you ran more iterations it would only get better. Looking back this was a very good class. Vlad On Apr 6, 2012, at 06:54 , Vlad Niculae wrote: > > On Apr 6, 2012, at 02:56 , Andreas Mueller wrote: > >> On 04/05/2012 11:17 PM, Vlad Niculae wrote: >>> I would like to see a reproduction of the standard neural net digits >>> example: >>> >>> http://ufldl.stanford.edu/wiki/images/8/84/SelfTaughtFeatures.png >>> >> That looks like the weights of an autoencoder, right? >> Autoencoders are not part of the plan as far as I was concerned. >> I don't think filters in an MLP will look like this "magically" unless you >> tune your regularization quite carefully. > > I remember doing the online machine learning class last year and just by > training a neural net with one hidden layer for digit classification and > visualizing the hidden layer, you would get something very similar to that, I > was quite surprised. I'm curious now, I'll look for that code. > >> >> ------------------------------------------------------------------------------ >> For Developers, A Lot Can Happen In A Second. >> Boundary is the first to Know...and Tell You. >> Monitor Your Applications in Ultra-Fine Resolution. Try it FREE! >> http://p.sf.net/sfu/Boundary-d2dvs2 >> _______________________________________________ >> Scikit-learn-general mailing list >> [email protected] >> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > ------------------------------------------------------------------------------ For Developers, A Lot Can Happen In A Second. Boundary is the first to Know...and Tell You. Monitor Your Applications in Ultra-Fine Resolution. Try it FREE! http://p.sf.net/sfu/Boundary-d2dvs2 _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
