Biological Cybernetics

, Volume 103, Issue 1, pp 79–85 | Cite as

Analysis and design of asymmetric Hopfield networks with discrete-time dynamics

Original Paper
First Online:
Received:
Accepted:

Abstract

The retrieval properties of the asymmetric Hopfield neural networks (AHNNs) with discrete-time dynamics are studied in this paper. It is shown that the asymmetry degree is an important factor influencing the network dynamics. Furthermore, a strategy for designing AHNNs of different sparsities is proposed. Numerical simulations show that AHNNs can perform as well as symmetric ones, and the diluted AHNNs have the virtues of small wiring cost and high pattern recognition quality.

Keywords

Asymmetric Hopfield network Discrete-time dynamics Diluted network 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Amari SI (1972) Characteristics of random nets of analog neuron-like elements. IEEE Trans Syst Man Cybern 2(5): 643–657CrossRefGoogle Scholar
  2. Amari SI (1977) Neural theory of association and concept-formation. Biol Cybern 26(3): 175–185CrossRefPubMedGoogle Scholar
  3. Amit DJ, Gutfreund H, Sompolinsky H (1985) Spin glass models of neural networks. Phys Rev A 32: 1007–1018CrossRefPubMedGoogle Scholar
  4. Arenzon JJ, Lemke N (1994) Simulating highly diluted neural networks. J Phys A: Math Gen 27: 5161–5165CrossRefGoogle Scholar
  5. Bornholdt S, Graudenz D (1992) General asymmetric neural networks and structure design by genetic algorithms. Neural Netw 5: 327–334CrossRefGoogle Scholar
  6. Chen TP, Amari SI (2001) Stability of asymmetric hopfield networks. IEEE Trans Neural Netw 12: 159–163CrossRefPubMedGoogle Scholar
  7. Cheng XZ, Dasgupta C, Singh MP (2000) Retrieval properties of a hopfield model with random asymmetric interactions. Neural Comput 12: 865–880CrossRefGoogle Scholar
  8. Eccles JC (1964) The physiology of synapses. Springer-Verlag, BerlinGoogle Scholar
  9. Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79: 2554–2558CrossRefPubMedGoogle Scholar
  10. Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81: 3088–3092CrossRefPubMedGoogle Scholar
  11. Jin T, Zhao H (2005) Pattern recognition using asymmetric attractor neural networks. Phys Rev E 72:066111Google Scholar
  12. Krauth W, Mezard M (1987) Learning algorithms with optimal stability in neural networks. J Phys A 20(11): L745–L752CrossRefGoogle Scholar
  13. Lee DL, Chuang TC (2005) Designing asymmetric hopfield-type associative memory with higher order hamming stability. IEEE Trans Neural Netw 16: 1464–1476CrossRefPubMedGoogle Scholar
  14. Liu D, Michel AN (1993) Cellular neural networks for associative memories. IEEE Trans Circuits Syst 40(2): 119–121CrossRefGoogle Scholar
  15. Liu XW, Chen TP (2002) A new result on the global convergence of hopfield neural networks. IEEE Trans Circuits Syst 49: 1514–1516CrossRefGoogle Scholar
  16. Matsuoka K (1992) Stability conditions for nonlinear continuous neural networks with asymmetric connection weights. Neural Netw 5: 495–500CrossRefGoogle Scholar
  17. Michel AN, Gray DL (1990) Analysis and synthesis of neural networks with lower block triangular interconnecting structure. IEEE Trans Circuits Syst 37: 1267–1283CrossRefGoogle Scholar
  18. Stauffer D, Aharony A, Costa LD, Adler J (2003) Efficient hopfield pattern recognition on a scale-free neural network. Eur Phys J B 32(3): 395–399CrossRefGoogle Scholar
  19. Treves A, Amit DJ (1988) Metastable states in asymmetrically diluted hopfield networks. J Phys A: Math Gen 21: 3155–3169CrossRefGoogle Scholar
  20. White JG, Southgate E, Thomson JN, Brenner S (1986) The structure of the nervous system of the nematode Caenorhabditis elegans. Philos Trans R Soc Lond 314: 1–340CrossRefGoogle Scholar
  21. Xu ZB, Hu GQ, Kwong CP (1996) Asymmetric hopfield-type networks: theory and applications. Neural Netw 9: 483–501CrossRefGoogle Scholar
  22. Yang H, Dillon TS (1994) Exponential stability and oscillation of hopfield graded response neural network. IEEE Trans Neural Netw 5: 719–729CrossRefPubMedGoogle Scholar
  23. Zhao H (2004) Designing asymmetric neural networks with associative memory. Phys Rev E 70:066137Google Scholar
  24. Zheng P, Tang W, Zhang J (2010a) Efficient continuous-time asymmetric hopfield networks for memory retrieval. Neural Comput. doi: 10.1162/neco.2010.05-09-1014
  25. Zheng P, Tang W, Zhang J (2010b) A simple method for designing efficient small-world neural networks. Neural Netw 23(2): 155–159CrossRefPubMedGoogle Scholar
  26. Zhuang X, Huang Y, Yu FA (1994) Design of hopfield content-addressable memories. IEEE Trans Signal Process 42(2): 492–495CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Pengsheng Zheng
    • 1
  • Jianxiong Zhang
    • 1
  • Wansheng Tang
    • 1
  1. 1.Institute of Systems EngineeringTianjin UniversityTianjinChina

Personalised recommendations