A New Local Bipolar Autoassociative Memory Based on External Inputs of Discrete Recurrent Neural Networks With Time Delay

In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving $(2m)^{n}$ memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.

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

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

[3]  Amin Shokrollahi,et al.  Nonbinary Associative Memory With Exponential Pattern Retrieval Capacity and Iterative Learning , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Marcos Eduardo Valle,et al.  A Robust Subspace Projection Autoassociative Memory Based on the M-Estimation Method , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Xiaodong Liu,et al.  Stability analysis for neural networks with time-varying delay , 2008, 2008 47th IEEE Conference on Decision and Control.

[6]  V. Gimenez-Martinez,et al.  A modified Hopfield auto-associative memory with improved capacity , 2000, IEEE Trans. Neural Networks Learn. Syst..

[7]  Zhigang Zeng,et al.  Global robust stability of uncertain delayed neural networks with discontinuous neuron activation , 2013, Neural Computing and Applications.

[8]  Pengsheng Zheng.  Threshold Complex-Valued Neural Associative Memory , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Jun Wang,et al.  Robustness Analysis of Global Exponential Stability of Recurrent Neural Networks in the Presence of Time Delays and Random Disturbances , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Amin Shokrollahi,et al.  A Non-Binary Associative Memory with Exponential Pattern Retrieval Capacity and Iterative Learning: Extended Results , 2013, ArXiv.

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

[12]  Marcos Eduardo Valle,et al.  Complex-Valued Recurrent Correlation Neural Networks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Haibo Jiang,et al.  A generalized bipolar auto-associative memory model based on discrete recurrent neural networks , 2015, Neurocomputing.

[14]  A. Michel,et al.  Dynamical Systems with Saturation Nonlinearities: Analysis and Design , 1994 .

[15]  Margarita Kuzmina.  The recalling process dynamics of associative memory neural networks in macrodynamical approach , 1995, Neural Networks.

[16]  Min Long,et al.  Existence and Exponential Stability of Multiple Periodic Solutions for a Multidirectional Associative Memory Neural Network , 2012, Neural Processing Letters.

[17]  Liang Ding,et al.  New conditions for global exponential stability of continuous-time neural networks with delays , 2011, Neural Computing and Applications.

[18]  Zhigang Zeng,et al.  Multistability of Neural Networks With Time-Varying Delays and Concave-Convex Characteristics , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Haibo He,et al.  A neural network based online learning and control approach for Markov jump systems , 2015, Neurocomputing.

[20]  Amin Shokrollahi,et al.  Exponential pattern retrieval capacity with non-binary associative memory , 2011, 2011 IEEE Information Theory Workshop.

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

[22]  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).

[23]  Derong Liu,et al.  A new synthesis approach for feedback neural networks based on the perceptron training algorithm , 1997, IEEE Trans. Neural Networks.

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

[25]  Ting Wang,et al.  Combined Convex Technique on Delay-Dependent Stability for Delayed Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[26]  G. Grassi,et al.  A new approach to design cellular neural networks for associative memories , 1997 .

[27]  Eva Kaslik,et al.  Impulsive hybrid discrete-time Hopfield neural networks with delays and multistability analysis , 2011, Neural Networks.

[28]  Huaguang Zhang,et al.  An LMI Approach to Stability Analysis of Reaction–Diffusion Cohen–Grossberg Neural Networks Concerning Dirichlet Boundary Conditions and Distributed Delays , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[29]  Tianping Chen,et al.  Multistability of Neural Networks With Mexican-Hat-Type Activation Functions , 2012, IEEE Transactions on Neural Networks and Learning Systems.

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

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

[32]  Huaguang Zhang,et al.  Simplified frequency method for stability and bifurcation of delayed neural networks in ring structure , 2013, Neurocomputing.

[33]  J. J. Yu,et al.  Novel stability criteria of T-S fuzzy hopfield neural networks with time-varying delays and uncertainties , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

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

[35]  Nagarajan Sukavanam,et al.  Stability analysis of robust adaptive hybrid position/force controller for robot manipulators using neural network with uncertainties , 2012, Neural Computing and Applications.