Design of high-capacity auto-associative memories based on the analysis of complex-valued neural networks

This paper presents a new design method for synthesizing associative memories based on the complex-valued neural networks with asynchronous and unbounded delays. Some sufficient criteria in terms of several inequalities, which can bring robustness to parameters of the complex-valued networks, are obtained to assure the existence, uniqueness and global exponential stability of equilibrium points for the addressed networks with mixed delays. The design procedure enables auto-associative memories to be synthesized with high storage capacity. The desired store patterns are retrieved by feeding proper probes through external inputs rather than initial conditions, which can avoid spurious memory patterns. The obtained results are much more general than the existed works. Finally, one numerical example is provided to illustrate the effectiveness of the obtained results.

[1]  Xu-Hua Yang,et al.  Synthesization of high-capacity auto-associative memories using complex-valued neural networks* , 2016 .

[2]  Jacek M. Zurada,et al.  Complex-valued multistate neural associative memory , 1996, IEEE Trans. Neural Networks.

[3]  Zengyun Wang,et al.  Global stability analysis for delayed complex-valued BAM neural networks , 2016, Neurocomputing.

[4]  Zhenjiang Zhao,et al.  Global exponential stability of impulsive complex-valued neural networks with both asynchronous time-varying and continuously distributed delays , 2016, Neural Networks.

[5]  Kazuyuki Murase,et al.  Single-layered complex-valued neural network for real-valued classification problems , 2009, Neurocomputing.

[6]  Masaki Kobayashi,et al.  Chaotic complex-valued bidirectional associative memory with a real-valued context part , 2013 .

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

[8]  Dong Xie,et al.  Global exponential stability of periodic solution for delayed complex-valued neural networks with impulses , 2016, Neurocomputing.

[9]  Masaki Kobayashi Member.  Gradient descent learning rule for complex-valued associative memories with large constant terms , 2016 .

[10]  Saleem A. Kassam,et al.  Channel Equalization Using Adaptive Complex Radial Basis Function Networks , 1995, IEEE J. Sel. Areas Commun..

[11]  Tülay Adali,et al.  Fully Complex Multi-Layer Perceptron Network for Nonlinear Signal Processing , 2002, J. VLSI Signal Process..

[12]  Zidong Wang,et al.  State estimation for two‐dimensional complex networks with randomly occurring nonlinearities and randomly varying sensor delays , 2014 .

[13]  D.-L. Lee,et al.  Improvements of Complex-Valued Hopfield Associative Memory by Using Generalized Projection Rules , 2006, IEEE Transactions on Neural Networks.

[14]  Tohru Nitta,et al.  Orthogonality of Decision Boundaries in Complex-Valued Neural Networks , 2004, Neural Computation.

[15]  Yukio Kosugi,et al.  Characteristics of the complex‐valued associative memory model having penalty term , 2000 .

[16]  Quanxin Zhu,et al.  Less conservative delay-dependent H∞ control of uncertain neural networks with discrete interval and distributed time-varying delays , 2015, Neurocomputing.

[17]  Akira Hirose,et al.  Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.

[18]  S. L. Goh,et al.  An Augmented Extended Kalman Filter Algorithm for Complex-Valued Recurrent Neural Networks , 2007, Neural Computation.

[19]  Noest.  Discrete-state phasor neural networks. , 1988, Physical review. A, General physics.

[20]  K. Aihara,et al.  Complex-Valued Multistate Associative Memory With Nonlinear Multilevel Functions for Gray-Level Image Reconstruction , 2009, IEEE Transactions on Neural Networks.

[21]  Narasimhan Sundararajan,et al.  Projection-Based Fast Learning Fully Complex-Valued Relaxation Neural Network , 2013, IEEE Transactions on Neural Networks and Learning Systems.

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

[23]  Sandip Banerjee,et al.  Stability and bifurcation analysis of delay induced tumor immune interaction model , 2014, Appl. Math. Comput..

[24]  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).

[25]  Xiaofeng Liao,et al.  Stability and Hopf bifurcation of a complex-valued neural network with two time delays , 2015 .