Comparing neural networks: a benchmark on growing neural gas, growing cell structures, and fuzzy ARTMAP
- 1 January 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 9 (6) , 1279-1291
- https://doi.org/10.1109/72.728377
Abstract
This article compares the performance of some recently developed incremental neural networks with the wellknown multilayer perceptron (MLP) on real-world data. The incremental networks are fuzzy ARTMAP (FAM), growing neural gas (GNG) and growing cell structures (GCS). The real-world datasets consist of four different datasets posing different challenges to the networks in terms of complexity of decision boundaries, overlapping between classes, and size of the datasets. The performance of the networks on the datasets is reported with respect to measure classification error, number of training epochs, and sensitivity toward variation of parameters. Statistical evaluations are applied to examine the significance of the results. The overall performance ranks in the following descending order: GNG, GCS, MLP, FAM.Keywords
This publication has 9 references indexed in Scilit:
- A quantitative study of experimental evaluations of neural network learning algorithms: Current research practiceNeural Networks, 1996
- Task-relevant relaxation network for visuo-motory systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Dynamic Cell Structure Learns Perfectly Topology Preserving MapNeural Computation, 1995
- Growing cell structures—A self-organizing network for unsupervised and supervised learningNeural Networks, 1994
- Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional mapsIEEE Transactions on Neural Networks, 1992
- SuperSAB: Fast adaptive back propagation with good scaling propertiesNeural Networks, 1990
- Backpropagation: past and futurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectorsBiological Cybernetics, 1976