1
|
Zhang Y, Chung FL, Wang S. Takagi-sugeno-kang fuzzy systems with dynamic rule weights. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2019. [DOI: 10.3233/jifs-182561] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Affiliation(s)
- Yuanpeng Zhang
- School of Medical Informatics, Nantong University, Nantong, China
- School of Digital Media, Jiangnan University, Wuxi, China
| | - Fu-Lai Chung
- Department of Computing, Hong Kong Polytechnic University, Hong Kong
| | - Shitong Wang
- School of Digital Media, Jiangnan University, Wuxi, China
| |
Collapse
|
2
|
Abstract
A class of data-reusing learning algorithms for real-time recurrent neural networks (RNNs) is analyzed. The analysis is undertaken for a general sigmoid nonlinear activation function of a neuron for the real time recurrent learning training algorithm. Error bounds and convergence conditions for such data-reusing algorithms are provided for both contractive and expansive activation functions. The analysis is undertaken for various configurations that are generalizations of a linear structure infinite impulse response adaptive filter.
Collapse
Affiliation(s)
- Danilo P. Mandic
- School of Information Systems, University of East Anglia, Norwich, NR4 7TJ, U.K
| |
Collapse
|
3
|
Mandic D, Chambers J. On the choice of parameters of the cost function in nested modular RNN's. ACTA ACUST UNITED AC 2000; 11:315-22. [DOI: 10.1109/72.839003] [Citation(s) in RCA: 18] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|