Improvement of cascade correlation learning algorithm with an evolutionary initialization

Hualou Liang; Guiliang Dai

doi:10.1016/S0020-0255(97)10071-8

Improvement of cascade correlation learning algorithm with an evolutionary initialization

Hualou Liang (Corresponding Author), Guiliang Dai

Research output: Journal article publication › Journal article › Academic research › peer-review

11 Citations (Scopus)

Abstract

Cascade Correlation (CC) as a constructive algorithm for artificial neural networks stands out for solving hard classification problems. In this note we propose an extension of this technique that uses genetic algorithm for finding a good initialization point and yields improved results. The performance of our method is demonstrated on benchmark problems.

Original language	English
Pages (from-to)	1-6
Number of pages	6
Journal	Information Sciences
Volume	112
Issue number	1-4
DOIs	https://doi.org/10.1016/S0020-0255(97)10071-8
Publication status	Published - 1998
Externally published	Yes

More information

10.1016/S0020-0255(97)10071-8

Cite this

@article{201e4c5d279b4fd0a613377c60de4839,

title = "Improvement of cascade correlation learning algorithm with an evolutionary initialization",

abstract = "Cascade Correlation (CC) as a constructive algorithm for artificial neural networks stands out for solving hard classification problems. In this note we propose an extension of this technique that uses genetic algorithm for finding a good initialization point and yields improved results. The performance of our method is demonstrated on benchmark problems.",

author = "Hualou Liang and Guiliang Dai",

year = "1998",

doi = "10.1016/S0020-0255(97)10071-8",

language = "English",

volume = "112",

pages = "1--6",

journal = "Information Sciences",

issn = "0020-0255",

publisher = "Elsevier Inc.",

number = "1-4",

}

TY - JOUR

T1 - Improvement of cascade correlation learning algorithm with an evolutionary initialization

AU - Liang, Hualou

AU - Dai, Guiliang

PY - 1998

Y1 - 1998

N2 - Cascade Correlation (CC) as a constructive algorithm for artificial neural networks stands out for solving hard classification problems. In this note we propose an extension of this technique that uses genetic algorithm for finding a good initialization point and yields improved results. The performance of our method is demonstrated on benchmark problems.

AB - Cascade Correlation (CC) as a constructive algorithm for artificial neural networks stands out for solving hard classification problems. In this note we propose an extension of this technique that uses genetic algorithm for finding a good initialization point and yields improved results. The performance of our method is demonstrated on benchmark problems.

UR - https://www.scopus.com/pages/publications/0032298859

U2 - 10.1016/S0020-0255(97)10071-8

DO - 10.1016/S0020-0255(97)10071-8

M3 - Journal article

SN - 0020-0255

VL - 112

SP - 1

EP - 6

JO - Information Sciences

JF - Information Sciences

IS - 1-4

ER -

Improvement of cascade correlation learning algorithm with an evolutionary initialization

Abstract

More information

Other files and links

Fingerprint

Cite this