Nonlinear Complex Neural Circuits Analysis and Design by q-Value Weighted Bounded Operator

Authors:
Hong Hu;Zhongzhi Shi
Affiliations:
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Science, Beijing, China 100191;Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Science, Beijing, China 100191
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Year:
2008

Citing 6
Cited 0

Families of OWA operators

Fuzzy Sets and Systems
A neural model of contour integration in the primary visual cortex

Neural Computation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
An Investigation of Fuzzy Combiners applied to a Hybrid Multi-neural System

SBRN '02 Proceedings of the VII Brazilian Symposium on Neural Networks (SBRN'02)
The equivalence between fuzzy logic systems and feedforward neural networks

IEEE Transactions on Neural Networks
Multiple network fusion using fuzzy logic

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Dynamical analysis of complex neural circuits, especially for chaotic nonlinear neural circuits is a difficult task. In this paper, a novel approach to understand the nonlinear dynamic attributes of a neural circuit by using approximate logical model of q-Value Weighted Bounded Operator is discussed, and we proved that if a neural circuit works in a non-chaotic way, a suitable fuzzy logical framework which is an approximate logical model of neural cells can be found and we can analyze or design such kind neural circuit similar to analyze or design a digit computer, but if a neural circuit works in a chaotic way, fuzzy logical frameworks of neural cells are different under different precisions, we should use a multi scale approximate police(see Def.5) for understanding the function of such neural system with arbitrary small precisions.