- Semi-supervised Learning with Deep Generative Models
- Neural Information Processing Systems 2014: NIPS 2014
- Book/source title
- 28th Annual Conference on Neural Information Processing Systems 2014
- Book/source subtitle
- December 8-13, 2014, Montreal, Canada
- Pages (from-to)
- Red Hook, NY: Curran
- Volume (Publisher)
- Advances in Neural Information Processing Systems: 1049-5258
- Volume (Serie)
- Document type
- Conference contribution
- Faculty of Science (FNWI)
- Informatics Institute (IVI)
The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones. Generative approaches have thus far been either inflexible, inefficient or non-scalable. We show that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.
- Final publisher version
- Proceedings title: 28th Annual Conference on Neural Information Processing Systems 2014: December 8-13, 2014, Montreal, Canada.
- Vol. 4
Publisher: Neural Information Processing Systems Foundation
Place of publication: La Jolla, CA
Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence, K.Q. Weinberger
If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library, or send a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.