๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

On the performance of higher order moment neural computation

โœ Scribed by W.A. Porter; W. Liu


Publisher
Elsevier Science
Year
1995
Tongue
English
Weight
440 KB
Volume
3
Category
Article
ISSN
1069-0115

No coin nor oath required. For personal study only.

โœฆ Synopsis


Four benchmark examples for evaluating neural network performance are considered. The performance of the higher order moment neural array, HOMNA, on these benchmarks is explored. Comparable results for backprop networks and ARTMAP networks are available in the literature. It is shown that HOMNA trains faster and gives equivalent or better performance than either of these two alternative neural formats.


๐Ÿ“œ SIMILAR VOLUMES


Systematic synthesis of parallel archite
โœ Elias S. Manolakos; Haris M. Stellakis ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 580 KB

Fine granularity parallel architectures for the ecient estimation of higher order statistics (HOS) are systematically derived in this paper. A uniยฎed methodology for constructing locally recursive algorithms and spaceยฑtime linear mapping operators that lead to highly pipelined architectures consisti