A Review of Online Learning in Supervised Neural Networks

Lakhmi JAIN, Manjeevan Seera, Chee Peng Lim, P. Balasubramaniam

Research output: Contribution to journalReview article

33 Citations (Scopus)

Abstract

Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feed forward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented
Original languageEnglish
Pages (from-to)491-509
Number of pages19
JournalNeural Computing and Applications
Volume25
Issue number3-4
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Neural networks
Network architecture
Recurrent neural networks
Fuzzy neural networks
Feedforward neural networks

Cite this

JAIN, Lakhmi ; Seera, Manjeevan ; Lim, Chee Peng ; Balasubramaniam, P. / A Review of Online Learning in Supervised Neural Networks. In: Neural Computing and Applications. 2014 ; Vol. 25, No. 3-4. pp. 491-509.
@article{97f3422043eb41ad9f4352351754cded,
title = "A Review of Online Learning in Supervised Neural Networks",
abstract = "Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feed forward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented",
keywords = "Neural networks, Online learning, Supervised learning",
author = "Lakhmi JAIN and Manjeevan Seera and Lim, {Chee Peng} and P. Balasubramaniam",
year = "2014",
doi = "10.1007/s00521-013-1534-4",
language = "English",
volume = "25",
pages = "491--509",
journal = "Proximity multi-sphere support vector clustering",
issn = "0941-0643",
publisher = "Springer",
number = "3-4",

}

JAIN, L, Seera, M, Lim, CP & Balasubramaniam, P 2014, 'A Review of Online Learning in Supervised Neural Networks', Neural Computing and Applications, vol. 25, no. 3-4, pp. 491-509. https://doi.org/10.1007/s00521-013-1534-4

A Review of Online Learning in Supervised Neural Networks. / JAIN, Lakhmi; Seera, Manjeevan; Lim, Chee Peng; Balasubramaniam, P.

In: Neural Computing and Applications, Vol. 25, No. 3-4, 2014, p. 491-509.

Research output: Contribution to journalReview article

TY - JOUR

T1 - A Review of Online Learning in Supervised Neural Networks

AU - JAIN, Lakhmi

AU - Seera, Manjeevan

AU - Lim, Chee Peng

AU - Balasubramaniam, P.

PY - 2014

Y1 - 2014

N2 - Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feed forward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented

AB - Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feed forward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented

KW - Neural networks

KW - Online learning

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=84921894745&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/review-online-learning-supervised-neural-networks

U2 - 10.1007/s00521-013-1534-4

DO - 10.1007/s00521-013-1534-4

M3 - Review article

VL - 25

SP - 491

EP - 509

JO - Proximity multi-sphere support vector clustering

JF - Proximity multi-sphere support vector clustering

SN - 0941-0643

IS - 3-4

ER -