Re: [Scikit-learn-general] Error function in the output layer of MLP

Thank you. I see the differences now. Your explanation should be put into the MLP docs :-) On Thu, Jun 7, 2012 at 2:27 AM, David Warde-Farley < warde...@iro.umontreal.ca> wrote: > On Wed, Jun 06, 2012 at 04:38:16PM +0800, xinfan meng wrote: > > Hi, all. I post this question to the list, since it

Re: [Scikit-learn-general] Error function in the output layer of MLP

On Wed, Jun 06, 2012 at 04:38:16PM +0800, xinfan meng wrote: > Hi, all. I post this question to the list, since it might be related to the > MLP being developed. > > I found two versions of the error function for output layer of MLP are used > in the literature. > > >1. \delta_o = (y-a) f'(z

Re: [Scikit-learn-general] Error function in the output layer of MLP

Yes, I think your explanation is correct. Thanks. Those notation differences really make me confused, given that MLP is much more complex than Perceptron. :-( On Wed, Jun 6, 2012 at 8:59 PM, David Marek wrote: > > On Wed, Jun 6, 2012 at 1:50 PM, xinfan meng wrote: >> >> I think these two delta

Re: [Scikit-learn-general] Error function in the output layer of MLP

On Wed, Jun 6, 2012 at 1:50 PM, xinfan meng wrote: > > I think these two delta_o have the same meaning. If you have "Pattern > Recognition and Machine Learning" by Bishop, you can find that Bishop use > exactly the second formula in the back propagation algorithm. I suspect > these two formulae le

Re: [Scikit-learn-general] Error function in the output layer of MLP

Thanks for your reply. I think these two delta_o have the same meaning. If you have "Pattern Recognition and Machine Learning" by Bishop, you can find that Bishop use exactly the second formula in the back propagation algorithm. I suspect these two formulae lead to the same update iterations, but

Re: [Scikit-learn-general] Error function in the output layer of MLP

Hi On Wed, Jun 6, 2012 at 10:38 AM, xinfan meng wrote: > Hi, all. I post this question to the list, since it might be related to > the MLP being developed. > > I found two versions of the error function for output layer of MLP are > used in the literature. > > >1. \delta_o = (y-a) f'(z) >

[Scikit-learn-general] Error function in the output layer of MLP

Hi, all. I post this question to the list, since it might be related to the MLP being developed. I found two versions of the error function for output layer of MLP are used in the literature. 1. \delta_o = (y-a) f'(z) http://ufldl.stanford.edu/wiki/index.php/Backpropagation_Algorithm 2.