A spintronic memristor bridge synapse circuit and the application in memrisitive cellular automata

Wang, Lidan; Wang, Xiaodong; Duan, Shukai; Li, Huifang

doi:10.1016/j.neucom.2015.04.061

Cited by 30 publications

(16 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hopfield networks tends to be one that has the ability to associate with data types. Experiments on the Hopfield networks for binary image convergence [2] was done to prove the point. Hopfield networks can even be used for solving TSP, optimization and other crucial problems.…”

Section: Introductionmentioning

confidence: 94%

Design of Memristive Hopfield Neural Network using Memristor Bridges

Monurajan¹,

Ruhanbevi²,

Manjula³

2018

IJET

View full text Add to dashboard Cite

Artificial Neural Networks are interconnection of neurons inspired from the biological neural network of the brain. ANN is claimed to rule the future, spreads its wings to various areas of interest to name a few such as optimization, information technology, cryptography, image processing and even in medical diagnosis. There are devices which possess synaptic behaviour, one such device is memristor. Bridge circuit of memristors can be combined together to form neurons. Neurons can be made into a network with appropriate parameters to store data or images. Hopfield neural networks are chosen to store the data in associative memory. Hopfield neural networks are a significant feature in ANN which are recurrent in nature and in general are used as associative memory and in solving optimization problems such as the Travelling Salesman Problem. The paper deals on the construction of memristive Hopfield neural network using memristor bridging circuit and its application in the associative memory. This paper also illustrates the experiment with mathematical equations and the associative memory concept of the network using Matlab.

show abstract

Section: Introductionmentioning

confidence: 94%

Design of Memristive Hopfield Neural Network using Memristor Bridges

Monurajan¹,

Ruhanbevi²,

Manjula³

2018

IJET

View full text Add to dashboard Cite

show abstract

“…It is generally known that memristor possesses the ability of simulating synapses [22][23][24][25][26][27][28]. More specifically, the memristor has variable memristance depending on external excitations, which are ideal for synaptic weight updating.…”

Section: Synaptic Circuit Design With Memristor Series and Parallel Cmentioning

confidence: 99%

Multiple memristor series–parallel connections with use in synaptic circuit design

Luo

Duan

et al. 2017

IET Circuits, Devices & Systems

Self Cite

View full text Add to dashboard Cite

With the increase of research interest on memristors, various single or multiple memristor configurations have been integrated with advanced complementary metal-oxide-semiconducor technology, which promises efficient implementations of synaptic connections in neuromorphic computing systems, or computing elements in signal processing systems. In this study, multiple memristors, both in series and parallel connections, and their characteristics are further studied including the transient behaviours when asynchronous change happens and the composite electric properties in steady state etc. Particularly, the specific conditions to reach steady state and produce composite memristive effects are presented in detail. Furthermore, several synaptic memristor circuits based on series and parallel connections are also discussed.

show abstract

“…According to several open published manuscripts [12][13][14][15][16][17][18][19][20][21], it is necessary to design a synaptic circuit for achieving weight storage. In [12], Kim et al presented a memristor bridge circuit consisting of four memristors that is able to perform zero, positive, and negative synaptic weights.…”

Section: Introductionmentioning

confidence: 99%

Spintronic memristor synapse and its RWC learning algorithm

Chen

Duan

Dong

et al. 2018

IET Circuits, Devices & Systems

Self Cite

View full text Add to dashboard Cite

As one of the most widely used memristor models, the spintronic memristor has become a promising candidate for the electronic synapse. Non-volatility, nanoscale geometries, binary data and multi-level information storage make the circuit simpler and consume less electricity. In this study, a new spintronic memristor synaptic circuit is proposed which can realise positive, zero and negative weights successfully. Furthermore, the circuits of the presented synaptic-based neuron and compact neural network are designed and an improved random weight change (RWC) algorithm is proposed. Compared with the traditional RWC algorithm, it has faster training speed and less training error. In addition, the neural network is applied to data prediction, the result of which is closer to real data. Finally, the correctness and effectiveness of the proposed network are verified via a series of computer simulations.

show abstract

A spintronic memristor bridge synapse circuit and the application in memrisitive cellular automata

Cited by 30 publications

References 32 publications

Design of Memristive Hopfield Neural Network using Memristor Bridges

Design of Memristive Hopfield Neural Network using Memristor Bridges

Multiple memristor series–parallel connections with use in synaptic circuit design

Spintronic memristor synapse and its RWC learning algorithm

Contact Info

Product

Resources

About