Bayesian training of mixture density networks

Lars U. Hjorth; Ian T. Nabney

doi:10.1109/IJCNN.2000.860813

Bayesian training of mixture density networks

Lars U. Hjorth, Ian T. Nabney

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Chapter in a book

3 Citations (Scopus)

Abstract

Mixture Density Networks (MDNs) are a well-established method for modelling the conditional probability density which is useful for complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we extend earlier research of a regularisation method for a special case of MDNs to the general case using evidence based regularisation and we show how the Hessian of the MDN error function can be evaluated using R-propagation. The method is tested on two data sets and compared with early stopping.

Original language	Undefined/Unknown
Title of host publication	Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. IJCNN 2000
Place of Publication	United States
Publisher	IEEE Computer Society
Pages	455-460
Number of pages	6
Volume	4
ISBN (Print)	9780769506197
DOIs	https://doi.org/10.1109/IJCNN.2000.860813
Publication status	Published - 1 Aug 2000

Keywords

Bayes methods, learning, artificial intelligence, neural nets, Bayesian training, MDN error function, mixture density networks, R-propagation, conditional probability density

Access to Document

10.1109/IJCNN.2000.860813

Handle.net

Persistent link

Cite this

@inbook{5b44102ee72d4525877555932dd4e0a1,

title = "Bayesian training of mixture density networks",

abstract = "Mixture Density Networks (MDNs) are a well-established method for modelling the conditional probability density which is useful for complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we extend earlier research of a regularisation method for a special case of MDNs to the general case using evidence based regularisation and we show how the Hessian of the MDN error function can be evaluated using R-propagation. The method is tested on two data sets and compared with early stopping.",

keywords = "Bayes methods, learning, artificial intelligence, neural nets, Bayesian training, MDN error function, mixture density networks, R-propagation, conditional probability density",

author = "Hjorth, {Lars U.} and Nabney, {Ian T.}",

year = "2000",

month = aug,

day = "1",

doi = "10.1109/IJCNN.2000.860813",

language = "Undefined/Unknown",

isbn = "9780769506197",

volume = "4",

pages = "455--460",

booktitle = "Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. IJCNN 2000",

publisher = "IEEE Computer Society",

address = "United States",

}

TY - CHAP

T1 - Bayesian training of mixture density networks

AU - Hjorth, Lars U.

AU - Nabney, Ian T.

PY - 2000/8/1

Y1 - 2000/8/1

N2 - Mixture Density Networks (MDNs) are a well-established method for modelling the conditional probability density which is useful for complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we extend earlier research of a regularisation method for a special case of MDNs to the general case using evidence based regularisation and we show how the Hessian of the MDN error function can be evaluated using R-propagation. The method is tested on two data sets and compared with early stopping.

AB - Mixture Density Networks (MDNs) are a well-established method for modelling the conditional probability density which is useful for complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we extend earlier research of a regularisation method for a special case of MDNs to the general case using evidence based regularisation and we show how the Hessian of the MDN error function can be evaluated using R-propagation. The method is tested on two data sets and compared with early stopping.

KW - Bayes methods, learning, artificial intelligence, neural nets, Bayesian training, MDN error function, mixture density networks, R-propagation, conditional probability density

U2 - 10.1109/IJCNN.2000.860813

DO - 10.1109/IJCNN.2000.860813

M3 - Chapter in a book

SN - 9780769506197

VL - 4

SP - 455

EP - 460

BT - Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. IJCNN 2000

PB - IEEE Computer Society

CY - United States

ER -