Design of Memristive Hopfield Neural Network using Memristor Bridges

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    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.

     

     


  • Keywords


    Bridge circuit, Hopfield neural network, Memristor.

  • References


      [1] B. Yegnanarayana, “Artificial Neural Networks”, PHI Learning. ISBN9788120312531.URLhttps://books.google.co.in/books?id=RTtvUVU_xL4C, 2009.

      [2] Lidan Wang, Xiaodong Wang, Shukai Duan, and Huifang Li, “A spintronic memristor bridge synapse circuit and the application in memrisitive cellular automata”, Neurocomputing, 167(Supplement C):346 – 351, ISSN 0925-2312. doi: https://doi.org/10.1016/j.neucom.2015. 04.061, 2015.

      [3] L. Chua. Memristor-the missing circuit element. IEEE Transactions on Circuit Theory, 18(5):507–519, ISSN 0018-9324. doi: 10.1109/TCT.1971.1083337, September 1971.

      [4] Dmitri B. Strukov, Gregory S. Snider, Duncan R. Stewart, and R. Stanley Williams. The missing memristor found. 453: 80 EP , URL http://dx.doi.org/10.1038/ nature06932, May 2008.

      [5] Lidan Wang, Huifang Li, Shukai Duan, Tingwen Huang, and Huamin Wang. Pavlov associative memory in a memristive neural network and its circuit implementation. Neurocomputing, 171(Supplement C):23 – 29, ISSN 0925-2312. doi: https://doi.org/10.1016/j.neucom.2015. 05.078, 2016.

      [6] S. G. Hu, Y. Liu, Z. Liu, T. P. Chen, J. J. Wang, Q. Yu, L. J. Deng, Y. Yin, and Sumio Hosaka. Associative memory realized by a reconfigurable memristive hopfield neural network. 6: 7522 EP –, Jun 2015. URL http://dx.doi.org/10.1038/ ncomms8522. Article.

      [7] Mikhail S. Tarkov, “Hopfield Network with Interneuronal Connections Based on Memristor Bridges, pages 196–203. Springer International Publishing, Cham, ISBN 978-3-319-406633. doi: 10.1007/978-3-319-40663-3 23, 2016.

      [8] Hyongsuk Kim, Maheshwar P. Sah, Changju Yang, Tam´as Roska, and Leon O. Chua. “Memristor Bridge-Based Artificial Neural Weighting Circuit”, Springer International Publishing, Cham, ISBN 978-3-319-02630-5. doi: 10.1007/978-3-319-02630-5 12. pages 249–265. 2014.

      [9] Shukai Duan, Yi Zhang, Xiaofang Hu, Lidan Wang, and Chuandong Li. “Memristor-based chaotic neural networks for associative memory”, Neural Computing and Applications, 25(6):1437–1445, ISSN 1433-3058. doi: 10. 1007/s00521-014-1633-x, Nov 2014.

      [10] Beiye Liu, Yiran Chen, Bryant Wysocki, and Tingwen Huang. ”Reconfigurable neuromorphic computing system with memristor-based synapse design”, Neural Processing Letters, 41(2):159–167, ISSN 1573-773X. doi: 10. 1007/s11063-013-9315-8, Apr 2015.

      [11] S. G. Hu, Y. Liu, Z. Liu, T. P. Chen, J. J. Wang, Q. Yu, L. J. Deng, Y. Yin, and Sumio Hosaka, “A memristive hopfield network for associative memory”, URL http://dx.doi.org/10.1038/protex.2015.070, July 2015.


 

View

Download

Article ID: 16447
 
DOI: 10.14419/ijet.v7i3.12.16447




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.