Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
1991-12-01
SCID: 54.1/gwysttb8
Discuss with AI
adaptive controlfuzzy systemsgeometric theory of fuzzy setsneural networks as dynamical systemsself-organization
Figures from the paper
Abstract (AI)
This work combines neural networks and fuzzy systems, presenting neural networks as trainable dynamical systems and developing mechanisms and principles of adaption, self-organization, convergence and global stability. It includes the new geometric theory of fuzzy sets, systems and associated memories, and shows how to apply fuzzy set theory to adaptive control and how to generate structured fuzzy systems with unsupervised neural techniques.
Key Findings
1
A new geometric theory of fuzzy sets, fuzzy systems, and associated memories is introduced.
2
Fuzzy set theory is applicable to adaptive control within the proposed framework.
3
Neural networks can be formulated and treated as trainable dynamical systems for machine intelligence.
4
Structured fuzzy systems can be generated using unsupervised neural techniques.
5
The work develops mechanisms and principles for adaptation, self-organization, convergence, and global stability in such systems.
Research Object
Neural networks and fuzzy systems viewed as trainable dynamical systems
Research Subject
Mechanisms and principles of adaptation, self-organization, convergence and global stability; geometric theory of fuzzy sets/systems and application to adaptive control and generation of structured fuzzy systems via unsupervised neural techniques
Publication Details
Publication Date
1991-12-01
Journal
Publisher
ISSN
Access Type
Author Information
Download PDF
Subscribe to digest