A novel memristive Hopfield neural network with application in associative memory

Memristor is a nanoscale electronic device that exhibits the synaptic characteristics in artificial neural network. Some valuable memristor-based synaptic circuits have been presented. However, the circuitry implementations of some simple neural network are still rarely involved before. This paper contributes to construct a novel memristive Hopfield neural network circuit. On one hand, an improved memristor bridge circuit is employed to realize synaptic operation which better performs zero, positive and negative synaptic weights without requiring any switches and inverters, and Pspice implementation scheme is also considered. On the other hand, the proposed bridge circuit greatly simplifies the structure of neural network, and reduces the conversion process between current and voltage signal. Furthermore, the associative memory in binary and color images is demonstrated on the basis of the proposed memristive network. A series of numerical simulations are designed to verify associative memory capability, and experimental results demonstrate the effectiveness of the proposed neural network via the cases of single-associative memory and multi-associative memory.

[1]  Leon O. Chua,et al.  A Circuit-Based Learning Architecture for Multilayer Neural Networks With Memristor Bridge Synapses , 2015, IEEE Transactions on Circuits and Systems I: Regular Papers.

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

[3]  Chuandong Li,et al.  A novel memristive electronic synapse-based Hermite chaotic neural network with application in cryptography , 2015, Neurocomputing.

[4]  Jinde Cao,et al.  Matrix measure strategies for exponential synchronization and anti-synchronization of memristor-based neural networks with time-varying delays , 2015, Appl. Math. Comput..

[5]  Shukai Duan,et al.  A spintronic memristor bridge synapse circuit and the application in memrisitive cellular automata , 2015, Neurocomputing.

[6]  Jinde Cao,et al.  Synchronization of memristor-based recurrent neural networks with two delay components based on second-order reciprocally convex approach , 2014, Neural Networks.

[7]  Xin Wang,et al.  Associate learning and correcting in a memristive neural network , 2013, Neural Computing and Applications.

[8]  A Weakly Connected Memristive Neural Network for Associative Memory , 2013, Neural Processing Letters.

[9]  Steve Furber,et al.  Neural systems engineering , 2007, Journal of The Royal Society Interface.

[10]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Lidan Wang,et al.  A Memristor-Based Scroll Chaotic System - Design, Analysis and Circuit Implementation , 2014, Int. J. Bifurc. Chaos.

[12]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[13]  Sumio Hosaka,et al.  Associative memory realized by a reconfigurable memristive Hopfield neural network , 2015, Nature Communications.

[14]  Demessie Girma,et al.  A Hopfield neural-network-based dynamic channel allocation with handoff channel reservation control , 2000, IEEE Trans. Veh. Technol..

[15]  M. Pickett,et al.  Phase transitions enable computational universality in neuristor-based cellular automata. , 2013, Nanotechnology.

[16]  Zhigang Zeng,et al.  Event-Triggering Load Frequency Control for Multiarea Power Systems With Communication Delays , 2016, IEEE Transactions on Industrial Electronics.

[17]  Shukai Duan,et al.  Multilayer RTD-memristor-based cellular neural networks for color image processing , 2015, Neurocomputing.

[18]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[19]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[20]  Jinde Cao,et al.  New synchronization criteria for memristor-based networks: Adaptive control and feedback control schemes , 2015, Neural Networks.

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

[22]  Leon O. Chua,et al.  Memristor Bridge Synapses , 2012, Proceedings of the IEEE.

[23]  Huamin Wang,et al.  Pavlov associative memory in a memristive neural network and its circuit implementation , 2016, Neurocomputing.

[24]  Jinde Cao,et al.  Stability analysis of reaction-diffusion uncertain memristive neural networks with time-varying delays and leakage term , 2016, Appl. Math. Comput..

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

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

[27]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[28]  Claudia Felser,et al.  A large family of filled skutterudites stabilized by electron count. , 2015, Nature communications.

[29]  I. Pavlov.  Conditioned Reflexes: An Investigation of the Physiological Activity of the Cerebral Cortex , 1929 .

[30]  Michel Verleysen,et al.  A high-storage capacity content-addressable memory and its learning algorithm , 1989 .

[31]  Zhigang Zeng,et al.  Lag Synchronization of Switched Neural Networks via Neural Activation Function and Applications in Image Encryption , 2015, IEEE Transactions on Neural Networks and Learning Systems.

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

[33]  I. Pavlov,et al.  Conditioned reflexes: An investigation of the physiological activity of the cerebral cortex. , 1929, Annals of neurosciences.

[34]  Chuandong Li,et al.  Memristor-based chaotic neural networks for associative memory , 2014, Neural Computing and Applications.