A multi-layer memristive recurrent neural network for solving static and dynamic image associative memory

Abstract Recent years have seen increased attention being given to recurrent neural networks in associative memory applications. The activation function is the core of the recurrent neural network for associative memory, but its hardware implementation is quite complicated. A novel multi-layer memristive recurrent neural network (MMRNN) is proposed, in which nano-scaled element memristor is employed as activation function. Its stability is proved by numerical analysis, which provides the theoretical premise for its application. There are three advantages: (i) Since the memristor is a passive device, the activation function circuit will be low power consumption; (ii) It can not only simplify the hardware circuit, but also facilitate the implementation of VLSI; (iii) MMRNN can realize the associative memory of both static and dynamic images. A series of theoretical analysis and numerical simulations demonstrated the effectiveness of the proposed MMRNN. The study helps to explore the dynamic image associative memory, and provides a new effective way to realize the associative memory of video.

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

[2]  Shukai Duan,et al.  Memristor Model and its Application for Chaos Generation , 2012, Int. J. Bifurc. Chaos.

[3]  José Roberto Castilho Piqueira,et al.  Phase Oscillatory Network and Visual Pattern Recognition , 2015, IEEE Transactions on Neural Networks and Learning Systems.

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

[5]  Zhigang Zeng,et al.  Complete stability of delayed recurrent neural networks with Gaussian activation functions , 2017, Neural Networks.

[6]  Zhigang Zeng,et al.  Adjusting Learning Rate of Memristor-Based Multilayer Neural Networks via Fuzzy Method , 2019, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[7]  Jun Wang,et al.  Global uniform asymptotic stability of memristor-based recurrent neural networks with time delays , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[8]  Shukai Duan,et al.  Modeling affections with memristor-based associative memory neural networks , 2017, Neurocomputing.

[9]  H. Matsueda,et al.  Singular-Value-Decomposition Analysis of Associative Memory in a Neural Network , 2016, 1608.08333.

[10]  Lili Wang,et al.  Dynamical analysis on the multistability of high-order neural networks , 2013, Neurocomputing.

[11]  J. Yang,et al.  Memristive switching mechanism for metal/oxide/metal nanodevices. , 2008, Nature nanotechnology.

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

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

[14]  Zhigang Zeng,et al.  Multistability of recurrent neural networks with time-varying delays and nonincreasing activation function , 2016, Neurocomputing.

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

[16]  Shukai Duan,et al.  A Memristive Multilayer Cellular Neural Network With Applications to Image Processing , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Shukai Duan,et al.  Memristor-Based Cellular Nonlinear/Neural Network: Design, Analysis, and Applications , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Leon O. Chua,et al.  Memristor Bridge Synapse-Based Neural Network and Its Learning , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Shukai Duan,et al.  Easily Cascaded Memristor-CMOS Hybrid Circuit for High-Efficiency Boolean Logic Implementation , 2018, Int. J. Bifurc. Chaos.

[20]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

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

[22]  Yin Yang,et al.  Memristor-Based Echo State Network With Online Least Mean Square , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[23]  Shukai Duan,et al.  A general memristor-based pulse coupled neural network with variable linking coefficient for multi-focus image fusion , 2018, Neurocomputing.

[24]  Haibo Jiang,et al.  A unified associative memory model based on external inputs of continuous recurrent neural networks , 2016, Neurocomputing.

[25]  Zhigang Zeng,et al.  Multistability of periodic delayed recurrent neural network with memristors , 2012, Neural Computing and Applications.