Journal article
Improvement of cascade correlation learning algorithm with an evolutionary initialization
Information sciences, v 112(1-4), pp 1-6
01 Dec 1998
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.
Metrics
Details
- Title
- Improvement of cascade correlation learning algorithm with an evolutionary initialization
- Creators
- Hualou Liang - Computing CenterGuiliang Dai - Computing Center
- Publication Details
- Information sciences, v 112(1-4), pp 1-6
- Publisher
- Elsevier
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems
- Web of Science ID
- WOS:000077048100001
- Scopus ID
- 2-s2.0-0032298859
- Other Identifier
- 991019320709104721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Information Systems