Radial basis function network for multi-task learning

Xuejun Liao; Lawrence Carin

Radial basis function network for multi-task learning

Xuejun Liao, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We extend radial basis function (RBF) networks to the scenario in which multiple correlated tasks are learned simultaneously, and present the corresponding learning algorithms. We develop the algorithms for learning the network structure, in either a supervised or unsupervised manner. Training data may also be actively selected to improve the network's generalization to test data. Experimental results based on real data demonstrate the advantage of the proposed algorithms and support our conclusions.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems
Pages	795-802
Number of pages	8
State	Published - Dec 1 2005
Externally published	Yes

Cite this

@inproceedings{260ea32e44b84000a015247cdb10de84,

title = "Radial basis function network for multi-task learning",

abstract = "We extend radial basis function (RBF) networks to the scenario in which multiple correlated tasks are learned simultaneously, and present the corresponding learning algorithms. We develop the algorithms for learning the network structure, in either a supervised or unsupervised manner. Training data may also be actively selected to improve the network's generalization to test data. Experimental results based on real data demonstrate the advantage of the proposed algorithms and support our conclusions.",

author = "Xuejun Liao and Lawrence Carin",

note = "Generated from Scopus record by KAUST IRTS on 2021-02-09",

year = "2005",

month = dec,

day = "1",

language = "English (US)",

isbn = "9780262232531",

pages = "795--802",

booktitle = "Advances in Neural Information Processing Systems",

}

TY - GEN

T1 - Radial basis function network for multi-task learning

AU - Liao, Xuejun

AU - Carin, Lawrence

N1 - Generated from Scopus record by KAUST IRTS on 2021-02-09

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We extend radial basis function (RBF) networks to the scenario in which multiple correlated tasks are learned simultaneously, and present the corresponding learning algorithms. We develop the algorithms for learning the network structure, in either a supervised or unsupervised manner. Training data may also be actively selected to improve the network's generalization to test data. Experimental results based on real data demonstrate the advantage of the proposed algorithms and support our conclusions.

AB - We extend radial basis function (RBF) networks to the scenario in which multiple correlated tasks are learned simultaneously, and present the corresponding learning algorithms. We develop the algorithms for learning the network structure, in either a supervised or unsupervised manner. Training data may also be actively selected to improve the network's generalization to test data. Experimental results based on real data demonstrate the advantage of the proposed algorithms and support our conclusions.

UR - http://www.scopus.com/inward/record.url?scp=38149099603&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780262232531

SP - 795

EP - 802

BT - Advances in Neural Information Processing Systems

ER -

Radial basis function network for multi-task learning

Abstract

Other files and links

Fingerprint

Cite this