Bidirectional associative memory with learning capability using simultaneous perturbation

Maeda, Yutaka; Wakamura, M.

doi:10.1016/j.neucom.2005.02.021

Cited by 10 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bidirectional associative memory (BAM) neural networks, which were first introduced by Kosto [15], can realize hetero-association. These neural networks have attracted a lot of attention of many researchers [2,4,3,5,6,11,12,16,17,19,18,23,24,26,27,[29][30][31] and found many important applications in pattern recognition, image processing, associative memory and optimization problems [14,22,20,25]. However, for the human brain associative memory, besides these basic functions, there are some other more complicated associative memory functions, such as many-to-many association, which associates a number of related events with one hit or several features.…”

Section: Introductionmentioning

confidence: 99%

Existence and Exponential Stability of Multiple Periodic Solutions for a Multidirectional Associative Memory Neural Network

Zhou

Wang

Long

2012

Neural Process Lett

View full text Add to dashboard Cite

The paper proposes several mathematical models of the multidirectional associative memory (MAM) neural network by analyzing its structure. A model of MAM with distributed delays is studied. Under some new assumptions on activation functions, 2 n 0 [m/2] invariant subsets of MAM are constructed. Then the existence and the exponential stability of 2 n 0 [m/2] periodic solutions located on invariant subsets are obtained by constructing a suitable Liapunov function and a Poincaré mapping. An estimating method of the exponential convergence rate is given. The obtained results are new to MAM neural networks. An example is given to illustrate the effectiveness of the results.

show abstract

Section: Introductionmentioning

confidence: 99%

Existence and Exponential Stability of Multiple Periodic Solutions for a Multidirectional Associative Memory Neural Network

Zhou

Wang

Long

2012

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…Recently, a class of two-layer heteroassociative neural network was widely studied by many researchers, and it has also been used in many fields such as image processing, pattern recognition, and automatic control [1][2][3]. In the existing literature, some results are about the existence and stability of the equilibrium of the BAM neural networks [4][5][6][7][8][9][10], and some results are about the existence and stability of the periodic solution of the BAM neural networks [10][11][12][13][14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Global exponential periodicity for BAM neural network with periodic coefficients and continuously distributed delays

Zhou

Liu

et al. 2008

Computers & Mathematics with Applications

View full text Add to dashboard Cite

By constructing a suitable Lyapunov function and using some analysis techniques, rather than employing the continuation theorem of coincidence degree theory as in other literature, a sufficient criterion is obtained to ensure the existence and global exponential stability of periodic solution for the bidirectional associative memory neural network with periodic coefficients and continuously distributed delays. The obtained result is less restrictive to the BAM neural network than the previously known criteria. And it can be applied to the BAM neural network in which signal transfer functions are neither bounded nor differentiable. In addition, an example and its numerical simulation are given to illustrate the effectiveness of the obtained result.

show abstract

“…Because of its simplicity, the learning rule is suitable for hardware implementation [7,8,9]. The learning scheme is applicable to recurrent neural networks as well [7,9].…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, the simultaneous perturbation scheme is proposed [10] and is suitable for the learning of RNNs and their hardware implementation [9,11]. The simultaneous perturbation optimization method requires only values of an evaluation function as mentioned.…”

Section: Introductionmentioning

confidence: 99%

FPGA Implementation of Pulse Density Hopfield Neural Network

Maeda

Fukuda

2007

2007 International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

In this paper, we present a FPGA Hopfield Neural Network system with learning capability using the simultaneous perturbation learning rule. In the neural network, outputs and internal values are represented by pulse train. That is, analog Hopfield Neural Network with pulse frequency representation is considered. The pulse density representation and the simultaneous perturbation enable the system with learning capability to easily implement as a hardware system.Details of the design are described. Some results are also shown to confirm a viability of the system configuration and the learning capability.

show abstract

Bidirectional associative memory with learning capability using simultaneous perturbation

Cited by 10 publications

References 19 publications

Existence and Exponential Stability of Multiple Periodic Solutions for a Multidirectional Associative Memory Neural Network

Existence and Exponential Stability of Multiple Periodic Solutions for a Multidirectional Associative Memory Neural Network

Global exponential periodicity for BAM neural network with periodic coefficients and continuously distributed delays

FPGA Implementation of Pulse Density Hopfield Neural Network

Contact Info

Product

Resources

About