HOW TO SOLVE THE N-BIT ENCODER PROBLEM WITH ONE HIDDEN UNIT AND POLYNOMIALLY INCREASING WEIGHTS AND THRESHOLDS

Authors
LIANG X XIA SW DU JH
Citation
X. Liang et al., HOW TO SOLVE THE N-BIT ENCODER PROBLEM WITH ONE HIDDEN UNIT AND POLYNOMIALLY INCREASING WEIGHTS AND THRESHOLDS, Neurocomputing, 7(1), 1995, pp. 85-87
Citations number
2
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence",Neurosciences
Journal title
Neurocomputing → ACNP
ISSN journal
09252312
Volume
7
Issue
1
Year of publication
1995
Pages
85 - 87
Database
ISI
SICI code
0925-2312(1995)7:1<85:HTSTNE>2.0.ZU;2-L
Abstract
This letter presents a more practical constructive method than that of Stork's [1] with just one hidden unit to the N-bit encoder problem, i n which the input weights and output thresholds are polynomially rathe r than exponentially increasing as N increases.