Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Hysteretic chaotic neural network for crossbar switch problems

  • Author(s): Wei Zhang 1, 2 ; Tian Le 1 ; Yuanhong Wu 1 ; Youfu Jiang 1 ; Ronggang Fan 3
    • View affiliations
  • Source: Volume 2018, Issue 16, November 2018, p. 1658 – 1661
    DOI:  10.1049/joe.2018.8288 , Online ISSN 2051-3305
This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 18/07/2018, Accepted 31/07/2018, Published 16/08/2018

A hysteretic chaotic neural network is proposed to solve the crossbar switch problem effectively. The chaotic neural network structure with hysteresis and its set computation characteristics are carried out. The simulation results show that the theory is corrected by simulating the chaotic neural network with randomly generated neurons. The network architecture is applied to the crossbar switch problem, and the results of the computer simulation are given to illustrate the computational capability of the network architecture. The simulation results show that the chaotic neural network structure with hysteresis neurons is better than the previous network structure for the crossbar switch problem in terms of cost, time, and optimal solution rate.

Inspec keywords: optimisation; hysteresis; chaos; digital simulation; neural nets

Other keywords: computer simulation; chaotic neural network structure; crossbar switch problem; network architecture; hysteretic chaotic neural network; set computation characteristics

Subjects: Simulation techniques; Optimisation techniques; Neural computing techniques

References

    1. 1)
      • 9. Hopfield, J.J., Tank, D.W.: ‘Neural’ computation of decisions in optimization problems’, Biol. Cybern., 1985, 52, pp. 141–152.
    2. 2)
      • 13. Li, Y., Tang, Z., Wang, R., et al: ‘A positively self-feedbacked Hopfield neural network for N-queens problem’, IEEE Trans. Circuits Syst., 2004, 3173, pp. 442–447.
    3. 3)
      • 2. Tank, D.W., Hopfield, J.J.: ‘Simple neural optimization network: an A/D converter, signal decision circuit, and linear programming circuit’, IEEE Trans. Circuits Syst., 1986, 33, (5), pp. 533–541.
    4. 4)
      • 11. Gang, Y., Junyan, Y., et al: ‘A TCNN filter algorithm to maximum clique problem’, Neurocomputing, 2009, 72, (4–6), pp. 1312–1318.
    5. 5)
      • 4. Chen, L., Aihara, K.: ‘Chaotic simulated annealing by a neural network model with transient chaos’, Neural Netw., 1995, 8, (6), pp. 915–930.
    6. 6)
      • 7. Danca, M.-F., et al: ‘Hidden chaotic sets in a Hopfield neural system’, Chaos Solitons Fractals, 2017, 103, pp. 144–150.
    7. 7)
      • 14. Marrakchi, A., Troudet, T.: ‘A neural net arbitrator for large crossbar packet-switches’, IEEE Trans. Circuits Syst., 1989, 36, (7), pp. 1039–1041.
    8. 8)
      • 3. Aihara, K., Takabe, T., Toyoda, M.: ‘Chaotic neural networks’, Phys. Lett. A, 2009, 144, (6), pp. 333–340.
    9. 9)
      • 6. Yu, W., Cao, J.D.: ‘Cryptography based on delayed chaotic neural networks’, Phys. Lett. A, 2006, 356, (4–5), pp. 333–338.
    10. 10)
      • 10. Xia, G., Tang, Z., Li, Y., et al: ‘A binary Hopfield neural network with hysteresis for large crossbar packet switches’, Neurocomputing, 2005, 67, pp. 417–425.
    11. 11)
      • 15. Troudet, T.P., Walterst, S.M.: ‘Neural network architecture for crossbar switch control’, IEEE Trans. Circuits Syst., 1991, 38, (1), pp. 42–56.
    12. 12)
      • 16. Xu, X.S., Tang, Z., Wang, J.H.: ‘A method to improve the transiently chaotic neural network’, Neurocomputing, 2005, 67, pp. 456–463.
    13. 13)
      • 12. Liu, X., Xiu, C.: ‘A novel hysteretic chaotic neural network and its applications’, Neurocomputing, 2007, 70, (13–15), pp. 2561–2565.
    14. 14)
      • 8. Hopfield, J.J.: ‘Neural network and physical systems with emergent collective computational abilities’, Proc. Natl. Acad. Sci. USA, 1982, 79, pp. 2554–2558.
    15. 15)
      • 5. Cavalieri, S., Russo, M.: ‘Improving Hopfield neural network performance by fuzzy logic-based coefficient tuning’, Neurocomputing, 1998, 18, (1–3), pp. 107–126.
    16. 16)
      • 1. Smith, K.A.: ‘Neural networks for combinatorial optimization: are view of more than a decade of research’, INFORMS J. Comput., 1999, 11, pp. 15–34.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2018.8288
Loading

Related content

content/journals/10.1049/joe.2018.8288
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address