A Ferroelectric Memristor-Based Transient Chaotic Neural Network for Solving Combinatorial Optimization Problems

A transient chaotic neural network (TCNN) is particularly useful for solving combinatorial optimization problems, and its hardware implementation based on memristors has attracted great attention recently. Although previously used filamentary memristors could provide the desired nonlinearity for implementing the annealing function of a TCNN, the controllability of filamentary switching still remains relatively poor, thus limiting the performance of a memristor-based TCNN. Here, we propose to use ferroelectric memristor to implement the annealing function of a TCNN. In the ferroelectric memristor, the conductance can be tuned by switching the lattice non-centrosymmetry-induced polarization, which is a nonlinear switching mechanism with high controllability. We first establish a ferroelectric memristor model based on a ferroelectric tunnel junction (FTJ), which exhibits the polarization-modulated tunnel conductance and the nucleation-limited-switching (NLS) behavior. Then, the conductance of the ferroelectric memristor is used as the self-feedback connection weight that can be dynamically adjusted. Based on this, a ferroelectric memristor-based transient chaotic neural network (FM-TCNN) is further constructed and applied to solve the traveling salesman problem (TSP). In 1000 runs for 10-city TSP, the FM-TCNN achieves a shorter average path distance, a 32.8% faster convergence speed, and a 2.44% higher global optimal rate than the TCNN.

[1]  Jang-Sik Lee,et al.  CMOS-compatible compute-in-memory accelerators based on integrated ferroelectric synaptic arrays for convolution neural networks , 2022, Science advances.

[2]  Yihong Chen,et al.  Ferroelectric photosensor network: an advanced hardware solution to real-time machine vision , 2021, Nature Communications.

[3]  Roberto Montemanni,et al.  A New Constructive Heuristic driven by Machine Learning for the Traveling Salesman Problem , 2021, Algorithms.

[4]  M. R. Mahmoodi,et al.  Combinatorial optimization by weight annealing in memristive hopfield networks , 2021, Scientific Reports.

[5]  Yong Wang,et al.  Ant colony optimization for traveling salesman problem based on parameters optimization , 2021, Applied Soft Computing.

[6]  F. Traversa,et al.  Global minimization via classical tunneling assisted by collective force field formation , 2021, Science advances.

[7]  Guofu Zhou,et al.  Highly Controllable and Silicon-Compatible Ferroelectric Photovoltaic Synapses for Neuromorphic Computing , 2020, iScience.

[8]  Ke Yang,et al.  Transiently chaotic simulated annealing based on intrinsic nonlinearity of memristors for efficient solution of optimization problems , 2020, Science Advances.

[9]  Weichuan Huang,et al.  Sub-nanosecond memristor based on ferroelectric tunnel junction , 2020, Nature Communications.

[10]  Guozhen Yang,et al.  Reproducible Ultrathin Ferroelectric Domain Switching for High‐Performance Neuromorphic Computing , 2019, Advanced materials.

[11]  Xi Chen,et al.  Solving Optimization Problems Through Fully Convolutional Networks: An Application to the Traveling Salesman Problem , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[12]  G. C. Qiao,et al.  A memristor-based transient chaotic neural network model and its application , 2019, Journal of Applied Physics.

[13]  Lin Sun,et al.  A Robust Artificial Synapse Based on Organic Ferroelectric Polymer , 2018, Advanced Electronic Materials.

[14]  F. Caravelli.  Asymptotic Behavior of Memristive Circuits , 2017, Entropy.

[15]  Nicolas Locatelli,et al.  Learning through ferroelectric domain dynamics in solid-state synapses , 2017, Nature Communications.

[16]  Massimiliano Di Ventra,et al.  Self-organization and solution of shortest-path optimization problems with memristive networks , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.

[17]  A. Alivisatos,et al.  Ferroelectric order in individual nanometre-scale crystals. , 2012, Nature materials.

[18]  J. Grollier,et al.  A ferroelectric memristor. , 2012, Nature materials.

[19]  M. Alexe,et al.  Electroresistance effects in ferroelectric tunnel barriers , 2010, 1006.1716.

[20]  Lin Zhao,et al.  A Novel Chaotic Neural Network With the Ability to Characterize Local Features and Its Application , 2009, IEEE Trans. Neural Networks.

[21]  T. Noh,et al.  Domain switching kinetics in disordered ferroelectric thin films. , 2007, Physical review letters.

[22]  Lipo Wang,et al.  A noisy chaotic neural network for solving combinatorial optimization problems: stochastic chaotic simulated annealing , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[24]  Yassine Saji,et al.  A discrete bat algorithm based on Lévy flights for Euclidean traveling salesman problem , 2021, Expert Syst. Appl..