Regularisation of mixture density networks
Regularisation of mixture density networks
- Author(s): L.U. Hjorth and I.T. Nabney
- DOI: 10.1049/cp:19991162
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
9th International Conference on Artificial Neural Networks: ICANN '99 — Recommend this title to your library
Thank you
Your recommendation has been sent to your librarian.
- Author(s): L.U. Hjorth and I.T. Nabney Source: 9th International Conference on Artificial Neural Networks: ICANN '99, 1999 p. 521 – 526
- Conference: 9th International Conference on Artificial Neural Networks: ICANN '99
- DOI: 10.1049/cp:19991162
- ISBN: 0 85296 721 7
- Location: Edinburgh, UK
- Conference date: 7-10 Sept. 1999
- Format: PDF
Mixture density networks (MDNs) are a well-established method for modelling complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we develop a Bayesian regularisation method for MDNs by an extension of the evidence procedure. The method is tested on two data sets and compared with early stopping.
Inspec keywords: Bayes methods; probability; maximum likelihood estimation; neural nets
Subjects: Neural nets; Other topics in statistics
Related content
content/conferences/10.1049/cp_19991162
pub_keyword,iet_inspecKeyword,pub_concept
6
6
