A memristor-based transient chaotic neural network model and its application

Transient chaotic neural networks (TCNNs) have shown promise in solving optimization problems but still suffer from slow convergence and being difficult to implement in hardware. In this paper, the HP memristor is introduced to a TCNN to develop a memristor-based transient chaotic neural network (MTCNN) model that is highly efficient, converges quickly, and has significant prospects for physical implementation. The proposed MTCNN makes full use of the nonlinearity and memory-related characteristics of memristors, and their conductance values are used as self-feedback connection weights that can be adjusted dynamically according to the annealing algorithm. The MTCNN model was applied to solve combinatorial optimization problems, including the channel assignment problem (CAP) of four cells and the traveling salesman problem (TSP) of 10 cities. In 500 runs, the MTCNN algorithm delivered a 5% higher optimal solution rate than the TCNN algorithm while using only 70% of its number of iterations in the CAP, and achieved a shorter average distance and a 40% higher convergence speed than the TCNN algorithm in the TSP.Transient chaotic neural networks (TCNNs) have shown promise in solving optimization problems but still suffer from slow convergence and being difficult to implement in hardware. In this paper, the HP memristor is introduced to a TCNN to develop a memristor-based transient chaotic neural network (MTCNN) model that is highly efficient, converges quickly, and has significant prospects for physical implementation. The proposed MTCNN makes full use of the nonlinearity and memory-related characteristics of memristors, and their conductance values are used as self-feedback connection weights that can be adjusted dynamically according to the annealing algorithm. The MTCNN model was applied to solve combinatorial optimization problems, including the channel assignment problem (CAP) of four cells and the traveling salesman problem (TSP) of 10 cities. In 500 runs, the MTCNN algorithm delivered a 5% higher optimal solution rate than the TCNN algorithm while using only 70% of its number of iterations in the CAP, and ...

[1]  Huafeng Yang,et al.  An electronic synaptic device based on HfO2TiOx bilayer structure memristor with self-compliance and deep-RESET characteristics. , 2018, Nanotechnology.

[2]  K. Aihara,et al.  Chaotic neural networks , 1990 .

[3]  Anilkumar P. Thakoor,et al.  High-resolution synaptic weights and hardware-in-the-loop learning , 1995, Electronic Imaging.

[4]  Miguel A. F. Sanjuán,et al.  Partially controlling transient chaos in the Lorenz equations , 2016, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[5]  Jianbin Qiu,et al.  Adaptive Fuzzy Control for Nontriangular Structural Stochastic Switched Nonlinear Systems With Full State Constraints , 2019, IEEE Transactions on Fuzzy Systems.

[6]  Nasser M. Nasrabadi,et al.  Cellular radio channel assignment using a modified Hopfield network , 1997 .

[7]  Sun Changchun,et al.  Generation of transient chaos from two-dimensional systems via a switching approach , 2013 .

[8]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[9]  W. K. Hale.  Frequency assignment: Theory and applications , 1980, Proceedings of the IEEE.

[10]  Di Su,et al.  Orthodontic Treatment Planning based on Artificial Neural Networks , 2019, Scientific Reports.

[11]  Gert Cauwenberghs,et al.  Dynamically Reconfigurable Silicon Array of Spiking Neurons With Conductance-Based Synapses , 2007, IEEE Transactions on Neural Networks.

[12]  D. Kunz,et al.  Channel assignment for cellular radio using neural networks , 1991 .

[13]  Zhenya He,et al.  Self-Organizing Transient Chaotic Neural Network for Cellular Channel Assignment , 2002, Neural Processing Letters.

[14]  Ru Huang,et al.  Engineering incremental resistive switching in TaOx based memristors for brain-inspired computing. , 2016, Nanoscale.

[15]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[16]  L. Chua.  Memristor-The missing circuit element , 1971 .

[17]  K. Lim,et al.  Tunable Resistive Switching Enabled by Malleable Redox Reaction in the Nano-Vacuum Gap. , 2019, ACS applied materials & interfaces.

[18]  Zhen Liu,et al.  Predicting House Price With a Memristor-Based Artificial Neural Network , 2018, IEEE Access.

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

[20]  K. Stefanski,et al.  Transient chaos measurements using finite-time Lyapunov exponents. , 2010, Chaos.

[21]  Kazuyuki Aihara,et al.  Chaotic simulated annealing by a neural network model with transient chaos , 1995, Neural Networks.

[22]  Kazuyuki Aihara,et al.  Adaptive annealing for chaotic optimization , 1996 .

[23]  Mansour Sheikhan,et al.  Transient chaotic neural network-based disjoint multipath routing for mobile ad-hoc networks , 2011, Neural Computing and Applications.

[24]  Sumio Hosaka,et al.  Handwritten-Digit Recognition by Hybrid Convolutional Neural Network based on HfO2 Memristive Spiking-Neuron , 2018, Scientific Reports.

[25]  Byung-Gook Park,et al.  System-Level Simulation of Hardware Spiking Neural Network Based on Synaptic Transistors and I&F Neuron Circuits , 2018, IEEE Electron Device Letters.

[26]  Zhenhong Jia,et al.  Improvement and Application of Transient Chaos Neural Networks , 2011 .

[27]  Sadiq M. Sait,et al.  A fast constructive algorithm for fixed channel assignment problem , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[28]  Yang Liu,et al.  Realization of a Power-Efficient Transmitter Based on Integrated Artificial Neural Network , 2018, IEEE Access.

[29]  Goutam Chakraborty,et al.  An efficient heuristic algorithm for channel assignment problem in cellular radio networks , 2001, IEEE Trans. Veh. Technol..

[30]  Jacek M. Zurada,et al.  Cellular Neural Networks With Transient Chaos , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.

[31]  Jianbin Qiu,et al.  Observer-Based Fuzzy Adaptive Event-Triggered Control for Pure-Feedback Nonlinear Systems With Prescribed Performance , 2019, IEEE Transactions on Fuzzy Systems.