User talk:Daviddlewis

Talkback
Q VVERTYVS (hm?) 13:24, 3 August 2014 (UTC)

Talkback
Qwertyus - OK, excellent, so Probabilistic Classification covers the range of approaches for creating calibrated classifiers. The choice would then be whether the Platt scaling page should become one on all univariate rescaling, or just on univariate logistic regression rescaling. Thoughts? Dave p.s. I hope I'm using this talk thing correctly. Feel free to write me at davelewis@DavidDLewis.com Daviddlewis (talk) 14:39, 3 August 2014 (UTC)


 * Let's discuss over at Talk:Platt scaling. I prefer to discuss these things in public, so that others can contribute and see the decisions made. Q VVERTYVS (hm?) 07:48, 4 August 2014 (UTC)