Stochastic Configuration Networks: Fundamentals and Algorithms

This paper contributes to the development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed SC networks (SCNs). In contrast to the existing randomized learning algorithms for single layer feed-forward...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on cybernetics Ročník 47; číslo 10; s. 3466 - 3479
Hlavní autori: Wang, Dianhui, Li, Ming
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.10.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Approximation algorithms
Classification
Computational modeling
Computer simulation
Data analytics
Data models
incremental learning
Machine learning
Machine learning algorithms
Neural networks
Randomization
randomized algorithms
Regression analysis
stochastic configuration networks (SCNs)
Stochastic processes
Training
universal approximation property
ISSN:2168-2267, 2168-2275, 2168-2275
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper contributes to the development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed SC networks (SCNs). In contrast to the existing randomized learning algorithms for single layer feed-forward networks, we randomly assign the input weights and biases of the hidden nodes in the light of a supervisory mechanism, and the output weights are analytically evaluated in either a constructive or selective manner. As fundamentals of SCN-based data modeling techniques, we establish some theoretical results on the universal approximation property. Three versions of SC algorithms are presented for data regression and classification problems in this paper. Simulation results concerning both data regression and classification indicate some remarkable merits of our proposed SCNs in terms of less human intervention on the network size setting, the scope adaptation of random parameters, fast learning, and sound generalization.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2168-2267
2168-2275
2168-2275
DOI:10.1109/TCYB.2017.2734043