Home > Research > Publications & Outputs > Lambda-perceptron: an adaptive classifier for ...

Research

Associated organisational unit

Electronic data

Links

Text available via DOI:

Keywords

View graph of relations

Lambda-perceptron: an adaptive classifier for data-streams

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Lambda-perceptron: an adaptive classifier for data-streams. / Pavlidis, N; Tasoulis, Dimitrios; Adams, N M et al.
In: Pattern Recognition, Vol. 44, No. 1, 01.2011, p. 78-96.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Pavlidis, N, Tasoulis, D, Adams, NM & Hand, DJ 2011, 'Lambda-perceptron: an adaptive classifier for data-streams', Pattern Recognition, vol. 44, no. 1, pp. 78-96. https://doi.org/10.1016/j.patcog.2010.07.026

APA

Pavlidis, N., Tasoulis, D., Adams, N. M., & Hand, D. J. (2011). Lambda-perceptron: an adaptive classifier for data-streams. Pattern Recognition, 44(1), 78-96. https://doi.org/10.1016/j.patcog.2010.07.026

Vancouver

Pavlidis N, Tasoulis D, Adams NM, Hand DJ. Lambda-perceptron: an adaptive classifier for data-streams. Pattern Recognition. 2011 Jan;44(1):78-96. doi: 10.1016/j.patcog.2010.07.026

Author

Pavlidis, N ; Tasoulis, Dimitrios ; Adams, N M et al. / Lambda-perceptron: an adaptive classifier for data-streams. In: Pattern Recognition. 2011 ; Vol. 44, No. 1. pp. 78-96.

Bibtex

@article{ac8f5e34b0a442ed830430ab28407ecd,
title = "Lambda-perceptron: an adaptive classifier for data-streams",
abstract = "Streaming data introduce challenges mainly due to changing data distributions (population drift). To accommodate population drift we develop a novel linear adaptive online classification method motivated by ideas from adaptive filtering. Our approach allows the impact of past data on parameter estimates to be gradually removed, a process termed forgetting, yielding completely online adaptive algorithms. Extensive experimental results show that this approach adjusts the forgetting mechanism to maintain performance. Moreover, it might be possible to exploit the information in the evolution of the forgetting mechanism to obtain information about the type and speed of the underlying population drift process.",
keywords = "Streaming data, Classification , Population drift , Online learning, Forgetting",
author = "N Pavlidis and Dimitrios Tasoulis and Adams, {N M} and Hand, {D J}",
year = "2011",
month = jan,
doi = "10.1016/j.patcog.2010.07.026",
language = "English",
volume = "44",
pages = "78--96",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Ltd",
number = "1",

}

RIS

TY - JOUR

T1 - Lambda-perceptron: an adaptive classifier for data-streams

AU - Pavlidis, N

AU - Tasoulis, Dimitrios

AU - Adams, N M

AU - Hand, D J

PY - 2011/1

Y1 - 2011/1

N2 - Streaming data introduce challenges mainly due to changing data distributions (population drift). To accommodate population drift we develop a novel linear adaptive online classification method motivated by ideas from adaptive filtering. Our approach allows the impact of past data on parameter estimates to be gradually removed, a process termed forgetting, yielding completely online adaptive algorithms. Extensive experimental results show that this approach adjusts the forgetting mechanism to maintain performance. Moreover, it might be possible to exploit the information in the evolution of the forgetting mechanism to obtain information about the type and speed of the underlying population drift process.

AB - Streaming data introduce challenges mainly due to changing data distributions (population drift). To accommodate population drift we develop a novel linear adaptive online classification method motivated by ideas from adaptive filtering. Our approach allows the impact of past data on parameter estimates to be gradually removed, a process termed forgetting, yielding completely online adaptive algorithms. Extensive experimental results show that this approach adjusts the forgetting mechanism to maintain performance. Moreover, it might be possible to exploit the information in the evolution of the forgetting mechanism to obtain information about the type and speed of the underlying population drift process.

KW - Streaming data

KW - Classification

KW - Population drift

KW - Online learning

KW - Forgetting

U2 - 10.1016/j.patcog.2010.07.026

DO - 10.1016/j.patcog.2010.07.026

M3 - Journal article

VL - 44

SP - 78

EP - 96

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 1

ER -