Chaos and asymptotical stability in discrete-time recurrent neural networks with generalized input-output function
DOI10.1007/BF02874421zbMath1006.65139MaRDI QIDQ1609628
Jin-Liang Wang, Luo-Nan Chen, Zhu-jun Jing
Publication date: 15 August 2002
Published in: Science in China. Series A (Search for Journal in Brave)
snap-back repeller; chaos; neural network; numerical examples; asymptotic stability; bifurcation; discrete time
65K10: Numerical optimization and variational techniques
93D15: Stabilization of systems by feedback
93C55: Discrete-time control/observation systems
93D25: Input-output approaches in control theory
93D20: Asymptotic stability in control theory
37D45: Strange attractors, chaotic dynamics of systems with hyperbolic behavior
65P20: Numerical chaos
37M20: Computational methods for bifurcation problems in dynamical systems
65P30: Numerical bifurcation problems
Related Items
Cites Work
- Unnamed Item
- ``Neural computation of decisions in optimization problems
- Snap-back repellers imply chaos in \(\mathbb{R}^n\)
- Stability in asymmetric Hopfield nets with transmission delays
- Chaos and asymptotical stability in discrete-time neural networks
- Weakly connected neural networks
- Qualitative analysis and synthesis of a class of neural networks
- Global searching ability of chaotic neural networks
- Neural networks and physical systems with emergent collective computational abilities.
- Neurons with graded response have collective computational properties like those of two-state neurons.
