Le 21 mars 2012 01:39, Olivier Grisel <[email protected]> a écrit : > Le 21 mars 2012 01:21, David Marek <[email protected]> a écrit : >> Hi >> >> I think I was a little confused, I'll try to summarize what I >> understand is needed: >> >> * the goal is to have multilayer perceptron with stochastic gradient >> descent and maybe other learning algorithms >> * basic implementation of sgd already exists >> * existing implementation is missing some loss-functions, we need to >> use some from sgd-fast and implement others >> * existing implementation is slow, the final implementation should be >> written in Cython >> >> Am I correct? > > It seems so. > >> I have experimented with Cython and realized that there will be work >> needed to make the mlp faster. > > Preallocating the arrays to store that activations and ...
Hum I forgot to end that part of the sentence... I meant: Preallocating the arrays to store the activations of the hidden and ouput units outside of the main backprop loop is probably very important too. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
