Iterative least squares functional networks classifier

Emad A. El-Sebakhy; Ali S. Hadi; Kanaan A. Faisal

doi:10.1109/TNN.2007.891632

Iterative least squares functional networks classifier

Emad A. El-Sebakhy^*, Ali S. Hadi, Kanaan A. Faisal

^*Corresponding author for this work

King Fahd University of Petroleum & Minerals

Research output: Contribution to journal › Article › peer-review

30 Scopus citations

Abstract

This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications. A comparative study with the most common classification algorithms in both machine learning and statistics communities is carried out. The study was achieved with only sets of second-order linearly independent polynomial functions to approximate the neuron functions. The results show that this new framework classifier is reliable, flexible, stable, and achieves a high-quality performance.

Original language	English
Pages (from-to)	844-850
Number of pages	7
Journal	IEEE Transactions on Neural Networks
Volume	18
Issue number	3
DOIs	https://doi.org/10.1109/TNN.2007.891632
State	Published - May 2007

Bibliographical note

Funding Information:
Manuscript received September 16, 2005; revised April 23, 2006 and October 11, 2006; accepted November 8, 2006. This work was supported by the Cornell University, Ithaca, NY; King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi Arabia; and Egyptian and Educational Bureau, Washington D.C.

Keywords

Functional networks
Minimum description length
Statistical pattern recognition

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/TNN.2007.891632

Cite this

@article{a2233687d4b04487b045d6ee8a0eeab6,

title = "Iterative least squares functional networks classifier",

abstract = "This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications. A comparative study with the most common classification algorithms in both machine learning and statistics communities is carried out. The study was achieved with only sets of second-order linearly independent polynomial functions to approximate the neuron functions. The results show that this new framework classifier is reliable, flexible, stable, and achieves a high-quality performance.",

keywords = "Functional networks, Minimum description length, Statistical pattern recognition",

author = "El-Sebakhy, \{Emad A.\} and Hadi, \{Ali S.\} and Faisal, \{Kanaan A.\}",

note = "Funding Information: Manuscript received September 16, 2005; revised April 23, 2006 and October 11, 2006; accepted November 8, 2006. This work was supported by the Cornell University, Ithaca, NY; King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi Arabia; and Egyptian and Educational Bureau, Washington D.C.",

year = "2007",

month = may,

doi = "10.1109/TNN.2007.891632",

language = "English",

volume = "18",

pages = "844--850",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

number = "3",

}

TY - JOUR

T1 - Iterative least squares functional networks classifier

AU - El-Sebakhy, Emad A.

AU - Hadi, Ali S.

AU - Faisal, Kanaan A.

N1 - Funding Information: Manuscript received September 16, 2005; revised April 23, 2006 and October 11, 2006; accepted November 8, 2006. This work was supported by the Cornell University, Ithaca, NY; King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi Arabia; and Egyptian and Educational Bureau, Washington D.C.

PY - 2007/5

Y1 - 2007/5

N2 - This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications. A comparative study with the most common classification algorithms in both machine learning and statistics communities is carried out. The study was achieved with only sets of second-order linearly independent polynomial functions to approximate the neuron functions. The results show that this new framework classifier is reliable, flexible, stable, and achieves a high-quality performance.

AB - This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications. A comparative study with the most common classification algorithms in both machine learning and statistics communities is carried out. The study was achieved with only sets of second-order linearly independent polynomial functions to approximate the neuron functions. The results show that this new framework classifier is reliable, flexible, stable, and achieves a high-quality performance.

KW - Functional networks

KW - Minimum description length

KW - Statistical pattern recognition

UR - https://www.scopus.com/pages/publications/34248648813

U2 - 10.1109/TNN.2007.891632

DO - 10.1109/TNN.2007.891632

M3 - Article

C2 - 17526349

AN - SCOPUS:34248648813

SN - 1045-9227

VL - 18

SP - 844

EP - 850

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 3

ER -

Iterative least squares functional networks classifier

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this