IEICE TRANSACTIONS on Fundamentals
A Fast Algorithm for Spatiotemporal Pattern Analysis of Neural Networks with Multivalued Logic
Summary :
This paper describes an efficient simulation algorithm for the spatiotemporal pattern analysis of the continuous-time neural networks with the multivalued logic (multivalued continuous-time neural networks). The multivalued transfer function of neuron is approximated to the stepwise constant function which is constructed by the sum of the step functions with the different thresholds. By this approximation, the dynamics of the network can be formulated as a stepwise constant linear differential equation at each timestep and the optimal timestep for the numerical integration can be obtained analytically. Finally, it is shown that the proposed method is much faster than a variety of conventional simulators.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E81-A No.9 pp.1847-1852
- Publication Date
- 1998/09/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Nonlinear Theory and Its Applications)
- Category
- Neural Networks
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hiroshi NINOMIYA, Atsushi KAMO, Teru YONEYAMA, Hideki ASAI, "A Fast Algorithm for Spatiotemporal Pattern Analysis of Neural Networks with Multivalued Logic" in IEICE TRANSACTIONS on Fundamentals,
vol. E81-A, no. 9, pp. 1847-1852, September 1998, doi: .
Abstract: This paper describes an efficient simulation algorithm for the spatiotemporal pattern analysis of the continuous-time neural networks with the multivalued logic (multivalued continuous-time neural networks). The multivalued transfer function of neuron is approximated to the stepwise constant function which is constructed by the sum of the step functions with the different thresholds. By this approximation, the dynamics of the network can be formulated as a stepwise constant linear differential equation at each timestep and the optimal timestep for the numerical integration can be obtained analytically. Finally, it is shown that the proposed method is much faster than a variety of conventional simulators.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e81-a_9_1847/_p
Copy
@ARTICLE{e81-a_9_1847,
author={Hiroshi NINOMIYA, Atsushi KAMO, Teru YONEYAMA, Hideki ASAI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Fast Algorithm for Spatiotemporal Pattern Analysis of Neural Networks with Multivalued Logic},
year={1998},
volume={E81-A},
number={9},
pages={1847-1852},
abstract={This paper describes an efficient simulation algorithm for the spatiotemporal pattern analysis of the continuous-time neural networks with the multivalued logic (multivalued continuous-time neural networks). The multivalued transfer function of neuron is approximated to the stepwise constant function which is constructed by the sum of the step functions with the different thresholds. By this approximation, the dynamics of the network can be formulated as a stepwise constant linear differential equation at each timestep and the optimal timestep for the numerical integration can be obtained analytically. Finally, it is shown that the proposed method is much faster than a variety of conventional simulators.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - A Fast Algorithm for Spatiotemporal Pattern Analysis of Neural Networks with Multivalued Logic
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1847
EP - 1852
AU - Hiroshi NINOMIYA
AU - Atsushi KAMO
AU - Teru YONEYAMA
AU - Hideki ASAI
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E81-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 1998
AB - This paper describes an efficient simulation algorithm for the spatiotemporal pattern analysis of the continuous-time neural networks with the multivalued logic (multivalued continuous-time neural networks). The multivalued transfer function of neuron is approximated to the stepwise constant function which is constructed by the sum of the step functions with the different thresholds. By this approximation, the dynamics of the network can be formulated as a stepwise constant linear differential equation at each timestep and the optimal timestep for the numerical integration can be obtained analytically. Finally, it is shown that the proposed method is much faster than a variety of conventional simulators.
ER -
English
