Analysis of associative memories based on cellular neural networks with value-varying templates

ABSTRACT In many research literatures, the dynamical behaviour of cellular neural networks (CNNs) is simplified by using cloning template. However, the flaws of cloning template are obvious, because the correlation between weights of cells in CNNs is enhanced. In order to overcome the shortcomings of cloning template, value-varying templates can be used in CNNs. In this paper, associative memories based on CNNs with value-varying templates are investigated. A criterion about stability of CNNs is presented. Then, the problem about obtaining parameters of CNNs can be translated into a problem of solving linear equations for each cell. A design procedure of associative memories is given by our theories and methods. From the procedure, the parameters of CNNs can be obtained. Finally, three examples are used to demonstrate the effectiveness of our theories and methods. And the results show that success rate of associative memories is higher than previous methods.

[1]  Chuandong Li,et al.  Analysis of associative memories based on stability of cellular neural networks with time delay , 2012, Neural Computing and Applications.

[2]  Pagavathigounder Balasubramaniam,et al.  Asymptotic stability of BAM neural networks of neutral-type with impulsive effects and time delay in the leakage term , 2011, Int. J. Comput. Math..

[3]  Z. H. Aghajari,et al.  A novel chaotic hetero-associative memory , 2015, Neurocomputing.

[4]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[5]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[6]  Derong Liu,et al.  A new synthesis procedure for a class of cellular neural networks with space-invariant cloning template , 1998 .

[7]  Yan Wang,et al.  A novel memristive Hopfield neural network with application in associative memory , 2017, Neurocomputing.

[8]  Zhigang Zeng,et al.  Design and Analysis of High-Capacity Associative Memories Based on a Class of Discrete-Time Recurrent Neural Networks , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Pagavathigounder Balasubramaniam,et al.  Global exponential stability for neutral-type BAM neural networks with time-varying delays , 2010, Int. J. Comput. Math..

[10]  Jun Peng,et al.  Analysis and design of associative memories based on stability of cellular neural networks , 2012, Neurocomputing.

[11]  Alexandre C. B. Delbem,et al.  Design of associative memories using cellular neural networks , 2009, Neurocomputing.

[12]  Zhigang Zeng,et al.  Analysis and Design of Associative Memories Based on Recurrent Neural Networks with Linear Saturation Activation Functions and Time-Varying Delays , 2007, Neural Computation.

[13]  Derong Liu,et al.  Cloning template design of cellular neural networks for associative memories , 1997 .

[14]  Zhigang Zeng,et al.  Pattern memory analysis based on stability theory of cellular neural networks , 2008 .

[15]  Y. Park,et al.  A synthesis procedure for associative memories based on space-varying cellular neural networks , 2001, Neural Networks.

[16]  Huaguang Zhang,et al.  Design and analysis of associative memories based on external inputs of delayed recurrent neural networks , 2014, Neurocomputing.

[17]  Chuandong Li,et al.  Analysis on equilibrium points of cellular neural networks with thresholding activation function , 2012, Neural Computing and Applications.

[18]  G. Grassi,et al.  On discrete-time cellular neural networks for associative memories , 2001 .

[19]  Derong Liu,et al.  Cellular neural networks for associative memories , 1993 .

[20]  Trung Kien Dang,et al.  Improving learning rule for fuzzy associative memory with combination of content and association , 2015, Neurocomputing.

[21]  Tingwen Huang,et al.  A neural network with a single recurrent unit for associative memories based on linear optimization , 2013, Neurocomputing.

[22]  R. Rakkiyappan,et al.  Stability results for stochastic bidirectional associative memory neural networks with multiple discrete and distributed time-varying delays , 2011, Int. J. Comput. Math..

[23]  Zhigang Zeng,et al.  Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions , 2012, Neurocomputing.

[24]  Zhigang Zeng,et al.  Memory pattern analysis of cellular neural networks , 2005 .

[25]  Girolamo Fornarelli,et al.  Adaptive particle swarm optimization for CNN associative memories design , 2009, Neurocomputing.

[26]  Chang Liu,et al.  Associative memory network and its hardware design , 2015, Neurocomputing.

[27]  Chuandong Li,et al.  Analysis on equilibrium points of cells in cellular neural networks described using cloning templates , 2012, Neurocomputing.

[28]  Zhigang Zeng,et al.  Associative memories based on continuous-time cellular neural networks designed using space-invariant cloning templates , 2009, Neural Networks.

[29]  Masaki Kobayashi,et al.  Chaotic pseudo-orthogonalized Hopfield associative memory , 2017, Neurocomputing.

[30]  Derong Liu,et al.  Sparsely interconnected neural networks for associative memories with applications to cellular neural networks , 1994 .