In this paper we propose a new discrete bidirectional associative memory (DBAM) which is derived from our previous continuous linear bidirectional associative memory (LBAM). The DBAM performs bidirectionally the opti...In this paper we propose a new discrete bidirectional associative memory (DBAM) which is derived from our previous continuous linear bidirectional associative memory (LBAM). The DBAM performs bidirectionally the optimal associative mapping proposed by Kohonen. Like LBAM and NBAM proposed by one of the present authors,the present BAM ensures the guaranteed recall of all stored patterns,and possesses far higher capacity compared with other existing BAMs,and like NBAM, has the strong ability to suppress the noise occurring in the output patterns and therefore reduce largely the spurious patterns. The derivation of DBAM is given and the stability of DBAM is proved. We also derive a learning algorithm for DBAM,which has iterative form and make the network learn new patterns easily. Compared with NBAM the present BAM can be easily implemented by software.展开更多
Globally coupled map (GCM) model can evolve through chaotic searching into several stable periodic orbits under properly controlled parameters. This can be exploited in information processing such as associative memor...Globally coupled map (GCM) model can evolve through chaotic searching into several stable periodic orbits under properly controlled parameters. This can be exploited in information processing such as associative memory and optimization. In this paper, we propose a novel covariance learning rule for multivalue patterns and apply it in memorization of gray scale images based on modified GCM model (S GCM). Analysis of retrieval results are given finally.展开更多
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 real...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.展开更多
文摘In this paper we propose a new discrete bidirectional associative memory (DBAM) which is derived from our previous continuous linear bidirectional associative memory (LBAM). The DBAM performs bidirectionally the optimal associative mapping proposed by Kohonen. Like LBAM and NBAM proposed by one of the present authors,the present BAM ensures the guaranteed recall of all stored patterns,and possesses far higher capacity compared with other existing BAMs,and like NBAM, has the strong ability to suppress the noise occurring in the output patterns and therefore reduce largely the spurious patterns. The derivation of DBAM is given and the stability of DBAM is proved. We also derive a learning algorithm for DBAM,which has iterative form and make the network learn new patterns easily. Compared with NBAM the present BAM can be easily implemented by software.
文摘Globally coupled map (GCM) model can evolve through chaotic searching into several stable periodic orbits under properly controlled parameters. This can be exploited in information processing such as associative memory and optimization. In this paper, we propose a novel covariance learning rule for multivalue patterns and apply it in memorization of gray scale images based on modified GCM model (S GCM). Analysis of retrieval results are given finally.
基金supported by Vietnam National Foundation for Science and Technology Development(NAFOSTED)(Grant No.102.99-2013.06)
文摘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.
