On Wed, Oct 19, 2011 at 8:42 AM, Lars Buitinck <[email protected]> wrote:
> Yes, by MaxEnt I meant the true multiclass version of LR rather than
> the OvA version. I put a note to this effect in the docstring, but
> I'll leave the narrative docs to someone who is more knowledgeable
> than me wrt. linear models.
>
Possible alternative names are "softmax" and "multinomial logit". Note
that "maximum entropy" is basically just exponential family maximum
likelihood and not specific to to multinomial LR.
http://en.wikipedia.org/wiki/Softmax_activation_function
http://en.wikipedia.org/wiki/Multinomial_logit
http://en.wikipedia.org/wiki/Exponential_family#Maximum_entropy_derivation
The multinomial logit page notes the use of MaxEnt to refer to multinomial
LR in the NLP community.
Jason
------------------------------------------------------------------------------
All the data continuously generated in your IT infrastructure contains a
definitive record of customers, application performance, security
threats, fraudulent activity and more. Splunk takes this data and makes
sense of it. Business sense. IT sense. Common sense.
http://p.sf.net/sfu/splunk-d2d-oct
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
