Bayesian training of Mixture Density Networks

被引：1

作者：

Hjorth, LU ^{[1
]}

Nabney, IT ^{[1
]}

机构：

[1] Aston Univ, Neural Comp Res Grp, Birmingham B4 7ET, W Midlands, England

来源：

IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL IV | 2000年

关键词：

D O I：

10.1109/IJCNN.2000.860813

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：455 / 460

页数：6

共 50 条

[1] Gaussian mixture models for training Bayesian convolutional neural networks
Mostafa, Bakhouya
Hassan, Ramchoun
Mohammed, Hadda
Tawfik, Masrour
[J]. EVOLUTIONARY INTELLIGENCE, 2024, 17 (04) : 2515 - 2536
[2] Pulp quality modelling using Bayesian mixture density neural networks
Orre, R
Lansner, A
[J]. JOURNAL OF SYSTEMS ENGINEERING, 1996, 6 (03): : 128 - 136
[3] Probabilistic electric load forecasting through Bayesian Mixture Density Networks
Brusaferri, Alessandro
Matteucci, Matteo
Spinelli, Stefano
Vitali, Andrea
[J]. APPLIED ENERGY, 2022, 309
[4] Mixture approximations to Bayesian networks
Tresp, V
Haft, M
Hofmann, R
[J]. UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1999, : 639 - 646
[5] BAYESIAN NEURAL NETWORKS AND DENSITY NETWORKS
MACKAY, DJC
[J]. NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 1995, 354 (01): : 73 - 80
[6] Graph Mixture Density Networks
Errica, Federico
Bacciu, Davide
Micheli, Alessio
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[7] Bayesian mixture modeling for spectral density estimation
Cadonna, Annalisa
Kottas, Athanasios
Prado, Raquel
[J]. STATISTICS & PROBABILITY LETTERS, 2017, 125 : 189 - 195
[8] Bayesian Mixture Labeling by Highest Posterior Density
Yao, Weixin
Lindsay, Bruce G.
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2009, 104 (486) : 758 - 767
[9] Regularisation of mixture density networks
Hjorth, LU
Nabney, IT
[J]. NINTH INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS (ICANN99), VOLS 1 AND 2, 1999, (470): : 521 - 526
[10] Survival Mixture Density Networks
Han, Xintian
Goldstein, Mark
Ranganath, Rajesh
[J]. MACHINE LEARNING FOR HEALTHCARE CONFERENCE, VOL 182, 2022, 182 : 224 - 248

← 1 2 3 4 5 →