A novel memristive neural network with hidden attractors and its circuitry implementation

Neural networks have been applied in various fields from signal processing, pattern recognition, associative memory to artifi- cial intelligence. Recently, nanoscale memristor has renewed interest in experimental realization of neural network. A neural network with a memristive synaptic weight is st...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Science China. Technological sciences Jg. 59; H. 3; S. 358 - 363
Hauptverfasser: Pham, Viet Thanh, Jafari, Sajad, Vaidyanathan, Sundarapandian, Volos, Christos, Wang, Xiong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Beijing Science China Press 01.03.2016
Schlagworte:
Engineering
Lyapunov指数
Poincaré映射
动力学性质
混沌吸引子
电路实现
神经网络
联想记忆
隐藏
equilibrium
hidden attractor
neural network
memristor
hyperchaos
ISSN:1674-7321, 1869-1900
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Neural networks have been applied in various fields from signal processing, pattern recognition, associative memory to artifi- cial intelligence. Recently, nanoscale memristor has renewed interest in experimental realization of neural network. A neural network with a memristive synaptic weight is studied in this work. Dynamical properties of the proposed neural network are investigated through phase portraits, Poincar6 map, and Lyapunov exponents. Interestingly, the memristive neural network can generate hyperchaotic attractors without the presence of equilibrium points. Moreover, circuital implementation of such memristive neural network is presented to show its feasibility.
Bibliographie:Neural networks have been applied in various fields from signal processing, pattern recognition, associative memory to artifi- cial intelligence. Recently, nanoscale memristor has renewed interest in experimental realization of neural network. A neural network with a memristive synaptic weight is studied in this work. Dynamical properties of the proposed neural network are investigated through phase portraits, Poincar6 map, and Lyapunov exponents. Interestingly, the memristive neural network can generate hyperchaotic attractors without the presence of equilibrium points. Moreover, circuital implementation of such memristive neural network is presented to show its feasibility.
11-5845/TH
neural network, memristor, hyperchaos, hidden attractor, equilibrium
ISSN:1674-7321
1869-1900
DOI:10.1007/s11431-015-5981-2