Quantizability and learning complexity in multilayer neural networks

被引：1

作者：

Fu, LM ^{[1
]}

机构：

[1] Univ Florida, Dept Comp & Informat Sci, Gainesville, FL 32611 USA

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS | 1998年 / 28卷 / 02期

基金：

美国国家科学基金会;

关键词：

generalization; learning complexity; machine learning; neural network; quantizability; sample complexity;

D O I：

10.1109/5326.669575

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The relationship between quantizability and learning complexity in multilayer neural networks is examined. In a special neural network architecture that calculates node activations according to the certainty factor (CF) model of expert systems, the analysis based upon quantizability leads to lower and also better estimates for generalization dimensionality and sample complexity than those suggested by the multilayer perceptron model. This analysis is further supported by empirical simulation results.

引用

页码：295 / 300

页数：6

共 50 条

[41] Complexity of Multiverse Networks and their Multilayer Generalization
Littwin, Etai
Wolf, Lior
2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 372 - 377
[42] Analytical description of the evolution of neural networks: learning rules and complexity
K. Holthausen
O. Breidbach
Biological Cybernetics, 1999, 81 : 169 - 175
[43] Analytical description of the evolution of neural networks: learning rules and complexity
Holthausen, K
Breidbach, O
BIOLOGICAL CYBERNETICS, 1999, 81 (02) : 169 - 175
[44] Learning in certainty-factor-based multilayer neural networks for classification
Univ of Florida, Gainesville, United States
IEEE Trans Neural Networks, 1 (151-158):
[45] IMPROVED LEARNING ALGORITHM FOR MULTILAYER NEURAL NETWORKS AND HANDWRITTEN NUMERAL RECOGNITION
YAMADA, K
NEC RESEARCH & DEVELOPMENT, 1990, (98): : 81 - 88
[46] THE OFFSET ALGORITHM - BUILDING AND LEARNING-METHOD FOR MULTILAYER NEURAL NETWORKS
MARTINEZ, D
ESTEVE, D
EUROPHYSICS LETTERS, 1992, 18 (2BIS): : 95 - 100
[47] In-Hardware Learning of Multilayer Spiking Neural Networks on a Neuromorphic Processor
Shrestha, Amar
Fang, Haowen
Rider, Daniel Patrick
Mei, Zaidao
Qiu, Qinru
2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2021, : 367 - 372
[48] The No-Prop algorithm: A new learning algorithm for multilayer neural networks
Widrow, Bernard
Greenblatt, Aaron
Kim, Youngsik
Park, Dookun
NEURAL NETWORKS, 2013, 37 : 180 - 186
[49] Ensembles of multilayer perceptron and modular neural networks for fast and accurate learning
Valdovinos, R. M.
Sanchez, J. S.
MICAI 2006: FIFTH MEXICAN INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2006, : 229 - +
[50] Dynamics of on-line gradient descent learning for multilayer neural networks
Saad, D
Solla, SA
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 302 - 308

← 1 2 3 4 5 →