alexa On Dis riminative vs. Generative lassi ers: A omparison of logisti regression and naive Bayes
Biomedical Sciences

Biomedical Sciences

International Journal of Biomedical Data Mining

Author(s): Andrew Y Ng, Mi hael I Jordan

Abstract Share this page

We ompare dis riminative and generative learning as typi ed by logisti regression and naive Bayes. We show, ontrary to a widelyheld belief that dis riminative lassi ers are almost always to be preferred, that there an often be two distin t regimes of performan e as the training set size is in reased, one in whi h ea h algorithm does better. This stems from the observation|whi h is borne out in repeated experiments|that while dis riminative learning has lower asymptoti error, a generative lassi er may also approa h its (higher) asymptoti error mu h faster.

  • To read the full article Visit
  • Open Access
This article was published in Advances in neural information processing systems and referenced in International Journal of Biomedical Data Mining

Relevant Expert PPTs

Relevant Speaker PPTs

Recommended Conferences

Peer Reviewed Journals
Make the best use of Scientific Research and information from our 700 + peer reviewed, Open Access Journals
International Conferences 2017-18
Meet Inspiring Speakers and Experts at our 3000+ Global Annual Meetings

Contact Us

© 2008-2017 OMICS International - Open Access Publisher. Best viewed in Mozilla Firefox | Google Chrome | Above IE 7.0 version