Skip to main content
SpringerLink
Log in

Designing pulse-coupled neural networks with spike-synchronization-dependent plasticity rule: image segmentation and memristor circuit application

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Pulse-coupled neural network (PCNN) is a powerful unsupervised learning model with many parameters to be determined empirically. In particular, the weight matrix is invariable in the iterative process, which is inconsistent with the actual biological system. Based on the existing research foundation of biology and neural network, we propose a spike-synchronization-dependent plasticity (SSDP) rule. In this paper, the mathematical model and algorithm of SSDP are presented. Furthermore, a novel memristor-based circuit model of SSDP is designed. Finally, experimental results demonstrate that SSDP has greatly improved the image processing capabilities of PCNN.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Bauer M, Oostenveld R, Peeters M, Fries P (2006) Tactile spatial attention enhances gamma-band activity in somatosensory cortex and reduces low-frequency activity in parieto-occipital areas. J Neurosci 26(2):490–501

    Google Scholar 

  2. Bi G, Poo M (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18(24):10464–10472

    Google Scholar 

  3. Bichot NP, Rossi AF, Desimone R (2005) Parallel and serial neural mechanisms for visual search in macaque area v4. Science 308(5721):529–534

    Google Scholar 

  4. Boybat I, Le Gallo M, Nandakumar S, Moraitis T, Parnell T, Tuma T, Rajendran B, Leblebici Y, Sebastian A, Eleftheriou E (2018) Neuromorphic computing with multi-memristive synapses. Nat Commun 9(1):2514

    Google Scholar 

  5. Brunet NM, Bosman CA, Vinck M, Roberts M, Oostenveld R, Desimone R, De Weerd P, Fries P (2014) Stimulus repetition modulates gamma-band synchronization in primate visual cortex. Proc Natl Acad Sci 111(9):3626–3631

    Google Scholar 

  6. Cao Y, Cao Y, Wen S, Zeng Z, Huang T (2019) Passivity analysis of reaction-diffusion memristor-based neural networks. Neural Netw 109:159–167

    MATH  Google Scholar 

  7. Cao Y, Wang S, Guo Z, Huang T, Wen S (2019) Synchronization of memristive neural networks with leakage delay and parameters mismatch via event-triggered control. Neural Netw 119:178–189

    MATH  Google Scholar 

  8. Chen Y, Ma Y, Kim DH, Park SK (2015) Region-based object recognition by color segmentation using a simplified PCNN. IEEE Trans Neural Netw Learn Syst 26(8):1682–1697

    MathSciNet  Google Scholar 

  9. Chua L (1971) Memristor-the missing circuit element. IEEE Trans Circuit Theory 18(5):507–519

    Google Scholar 

  10. Ding S, Wang Z (2017) Lag quasi-synchronization for memristive neural networks with switching jumps mismatch. Neural Comput Appl 28(12):4011–4022

    Google Scholar 

  11. Dong M, Wen S, Zeng Z, Yan Z, Huang T (2019) Sparse fully convolutional network for face labeling. Neurocomputing 331:465–472

    Google Scholar 

  12. Eckhorn R, Reitboeck HJ, Arndt M, Dicke P (1990) Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex. Neural Comput 2(3):293–307

    Google Scholar 

  13. Ekblad U, Kinser JM, Atmer J, Zetterlund N (2004) The intersecting cortical model in image processing. Nuclear Instrum Methods Phys Res Sect A Accel Spectrom Detect Assoc Equip 525(1–2):392–396

    Google Scholar 

  14. Eryilmaz SB, Joshi S, Neftci E, Wan W, Cauwenberghs G, Wong HSP (2016) Neuromorphic architectures with electronic synapses. In: 2016 17th international symposium on quality electronic design (ISQED), IEEE, pp 118–123

  15. Fell J, Fernandez G, Klaver P, Elger CE, Fries P (2003) Is synchronized neuronal gamma activity relevant for selective attention? Brain Res Rev 42(3):265–272

    Google Scholar 

  16. Fries P (2009) Neuronal gamma-band synchronization as a fundamental process in cortical computation. Ann Rev Neurosci 32:209–224

    Google Scholar 

  17. Fu J, Chen C, Chai J, Wong ST, Li I (2010) Image segmentation by EM-based adaptive pulse coupled neural networks in brain magnetic resonance imaging. Comput Med Imaging Graph 34(4):308–320

    Google Scholar 

  18. Gelasca ED, Byun J, Obara B, Manjunath B (2008) Evaluation and benchmark for biological image segmentation. In: 2008 15th IEEE international conference on image processing, IEEE, pp 1816–1819

  19. Gray CM, König P, Engel AK, Singer W (1989) Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties. Nature 338(6213):334

    Google Scholar 

  20. Gross J, Schnitzler A, Timmermann L, Ploner M (2007) Gamma oscillations in human primary somatosensory cortex reflect pain perception. PLoS Biol 5(5):e133

    Google Scholar 

  21. Gu X, Yu D, Zhang L (2005) Image shadow removal using pulse coupled neural network. IEEE Trans Neural Netw 16(3):692–698

    Google Scholar 

  22. Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36

    Google Scholar 

  23. Hebb DO (1949) The organization of behavior; a neuropsychological theory. Wiley, London, pp 62–78

    Google Scholar 

  24. Hua Y, Gu X (2017) Visual saliency using unit-linking pcnn image segmentation. In: 2017 13th international conference on natural computation, Fuzzy systems and knowledge discovery (ICNC-FSKD), IEEE, pp 879–883

  25. Huang W, Jing Z (2007) Multi-focus image fusion using pulse coupled neural network. Pattern Recognit Lett 28(9):1123–1132

    Google Scholar 

  26. Jin Y, Zhang W, Li P (2018) Hybrid macro/micro level backpropagation for training deep spiking neural networks. In: Advances in neural information processing systems, pp 7005–7015

  27. Johnson JL (1994) Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images. Appl Opt 33(26):6239–6253

    Google Scholar 

  28. Johnson JL (1994) Pulse-coupled neural networks. In: Adaptive computing: mathematics, electronics, and optics: a critical review, international society for optics and photonics, vol 10277, p 1027705

  29. Johnson JL, Padgett ML (1999) Pcnn models and applications. IEEE Trans Neural Netw 10(3):480–498

    Google Scholar 

  30. Kasabov NK (2018) Time-space, spiking neural networks and brain-inspired artificial intelligence, vol 7. Springer, Berlin

    Google Scholar 

  31. Kinser JM (1996) Simplified pulse-coupled neural network. In: Applications and science of artificial neural networks II, international society for optics and photonics, vol 2760, pp 563–568

  32. Li T, Duan S, Liu J, Wang L (2018) An improved design of RBF neural network control algorithm based on spintronic memristor crossbar array. Neural Comput Appl 30(6):1939–1946

    Google Scholar 

  33. Li Z, Dong M, Wen S, Hu X, Zhou P, Zeng Z (2019) CLU-CNNs: object detection for medical images. Neurocomputing 350:53–59

    Google Scholar 

  34. Ma YD, Dai RL, Li L (2001) A new algorithm of image segmentation based on pulse-coupled neural networks and the entropy of images. In: Proceedings of the 30th international conference neural information processing

  35. Markram H, Lübke J, Frotscher M, Sakmann B (1997) Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs. Science 275(5297):213–215

    Google Scholar 

  36. Ni Q, Gu X (2014) Video attention saliency mapping using pulse coupled neural network and optical flow. In: 2014 international joint conference on neural networks (IJCNN), IEEE, pp 340–344

  37. Ota Y (2002) VLSI structure for static image processing with pulse-coupled neural network. In: IEEE 2002 28th annual conference of the industrial electronics society. IECON 02, IEEE, vol 4, pp 3221–3226

  38. Panda P, Aketi A, Roy K (2019) Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization. arXiv preprint arXiv:191013931

  39. Ren G, Cao Y, Wen S, Zeng Z, Huang T (2018) A modified Elman neural network with a new learning rate. Neurocomputing 286:11–18

    Google Scholar 

  40. Riehle A, Grün S, Diesmann M, Aertsen A (1997) Spike synchronization and rate modulation differentially involved in motor cortical function. Science 278(5345):1950–1953

    Google Scholar 

  41. Strukov DB, Snider GS, Stewart DR, Williams RS (2008) The missing memristor found. Nature 453(7191):80

    Google Scholar 

  42. Sun B, Wen S, Wang S, Huang T, Li P, Chen Y (2019) Quantized synchronization of memristor-based neural networks via super-twisting algorithm. Neurocomputing 0:1–10

    Google Scholar 

  43. Taha AA, Hanbury A (2015) Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging 15(1):29

    Google Scholar 

  44. Vinck M, Womelsdorf T, Buffalo EA, Desimone R, Fries P (2013) Attentional modulation of cell-class-specific gamma-band synchronization in awake monkey area v4. Neuron 80(4):1077–1089

    Google Scholar 

  45. Waldemark J, Millberg M, Lindblad T, Waldemark K, Becanovic V (2000) Implementation of a pulse coupled neural network in FPGA. Int J Neural Syst 10(03):171–177

    Google Scholar 

  46. Wang M, Xu X, Wang G, Ding S, Sun T (2017) Medical images segmentation based on improved three-dimensional pulse coupled neural network. Int J Wirel Mob Comput 13(1):72–77

    Google Scholar 

  47. Wang S, Cao Y, Huang T, Wen S (2019) Passivity and passification of memristive neural networks with leakage term and time-varying delays. Appl Math Comput 361:294–310

    MathSciNet  MATH  Google Scholar 

  48. Wang S, Cao Y, Huang T, Chen Y, Li P, Wen S (2020) Sliding mode control of neural networks via continuous or periodic sampling event-triggering algorithm. Neural Netw 121:140–147

    MATH  Google Scholar 

  49. Wang Y, Cao Y, Guo Z, Wen S (2019) Passivity and passification of memristive recurrent neural networks with multi-proportional delays and impulse. Appl Math Comput 0:1–10

    MATH  Google Scholar 

  50. Wang Z, Wang S, Guo L (2018) Novel multi-focus image fusion based on pcnn and random walks. Neural Comput Appl 29(11):1101–1114

    Google Scholar 

  51. Wen S, Huang T, Yu X, Chen MZ, Zeng Z (2016) Aperiodic sampled-data sliding-mode control of fuzzy systems with communication delays via the event-triggered method. IEEE Trans Fuzzy Syst 24:1048–1057

    Google Scholar 

  52. Wen S, Chen MZ, Yu X, Zeng Z, Huang T (2017) Fuzzy control for uncertain vehicle active suspension systems via dynamic sliding-mode approach. IEEE Trans Syst Man Cyber Syst 47:24–32

    Google Scholar 

  53. Wen S, Xie X, Yan Z, Huang T, Zeng Z (2018) General memristor with applications in multilayer neural networks. Neural Netw 103:142–149

    Google Scholar 

  54. Wen S, Liu W, Yang Y, Zeng Z, Huang T (2019) Generating realistic videos from keyframes with concatenated GANs. IEEE Trans Circuits Syst Video Technol 29:2337–2348

    Google Scholar 

  55. Wen S, Wei H, Yan Z, Guo Z, Yang Y, Huang T, Chen Y (2019) Memristor-based design of sparse compact convolutional neural networks. IEEE Trans Netw Sci Eng 99:1–11

    Google Scholar 

  56. Wen S, Wei H, Yang Y, Guo Z, Zeng Z, Huang T, Chen Y (2019) Memristive LSTM networks for sentiment analysis. IEEE Trans Syst Man Cybern Syst 99:1–11

    Google Scholar 

  57. Xiao S, Xie X, Wen S, Zeng Z, Huang T, Jiang J (2018) GST-memristor-based online learning neural networks. Neurocomputing 272:677–682

    Google Scholar 

  58. Xie X, Wen S, Zeng Z, Huang T (2018) Memristor-based circuit implementation of pulse-coupled neural network with dynamical threshold generators. Neurocomputing 284:10–16

    Google Scholar 

  59. Xie X, Zou L, Wen S, Zeng Z, Huang T (2019) A flux-controlled logarithmic memristor model and emulator. Circuits Syst Signal Process 38(4):1452–1465

    Google Scholar 

  60. Xiong Y, Han WH, Zhao K, Zhang YB, Yang FH (2010) An analog CMOS pulse coupled neural network for image segmentation. In: 2010 10th IEEE international conference on solid-state and integrated circuit technology, IEEE, pp 1883–1885

  61. Xu X, Wang G, Ding S, Cheng Y, Wang X (2017) Pulse-coupled neural networks and parameter optimization methods. Neural Comput Appl 28(1):671–681

    Google Scholar 

  62. Yan Z, Liu W, Wen S, Yang Y (2019) Multi-label image classification by feature attention network. IEEE Access 7:98005–98013

    Google Scholar 

  63. Yin M, Liu X, Liu Y, Chen X (2018) Medical image fusion with parameter-adaptive pulse coupled neural network in nonsubsampled shearlet transform domain. IEEE Trans Instrum Meas 99:1–16

    Google Scholar 

  64. Yonekawa M, Kurokawa H (2009) An automatic parameter adjustment method of pulse coupled neural network for image segmentation. In: International conference on artificial neural networks, Springer, pp 834–843

  65. Zeng X, Wen S, Zeng Z, Huang T (2018) Design of memristor-based image convolution calculation in convolutional neural network. Neural Comput Appl 30:502–508

    Google Scholar 

  66. Zhan K, Zhang H, Ma Y (2009) New spiking cortical model for invariant texture retrieval and image processing. IEEE Trans Neural Netw 20(12):1980–1986

    Google Scholar 

  67. Zhan K, Shi J, Li Q, Teng J, Wang M (2015) Image segmentation using fast linking SCM. In: 2015 international joint conference on neural networks (IJCNN), IEEE, pp 1–8

  68. Zhan K, Teng J, Shi J, Li Q, Wang M (2016) Feature-linking model for image enhancement. Neural Comput 28(6):1072–1100

    MathSciNet  MATH  Google Scholar 

  69. Zhan K, Shi J, Wang H, Xie Y, Li Q (2017) Computational mechanisms of pulse-coupled neural networks: a comprehensive review. Arch Comput Methods Eng 24(3):573–588

    MathSciNet  MATH  Google Scholar 

  70. Zhu S, Wang L, Duan S (2017) Memristive pulse coupled neural network with applications in medical image processing. Neurocomputing 227:149–157

    Google Scholar 

Download references

Acknowledgements

This work was supported by the Natural Science Foundation of China under Grants 61673187 and 61673188. This publication was made possible by NPRP Grant: NPRP 8-274-2-107 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the author.

Author information

Authors and Affiliations

  1. School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, China

    Xudong Xie

  2. Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China

    Shiping Wen

  3. Centre for Artificial Intelligence, University of Technology Sydney, Ultimo, 2007, Australia

    Zheng Yan

  4. Science Program, Texas A & M University at Qatar, 23874, Doha, Qatar

    Tingwen Huang

  5. Department of Electrical and Computer Engineering, Duke University, Durham, NC, 27708, USA

    Yiran Chen

Authors
  1. Xudong Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shiping Wen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zheng Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tingwen Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yiran Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shiping Wen.

Ethics declarations

Conflict of interest

There is no conflict of interest in this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xie, X., Wen, S., Yan, Z. et al. Designing pulse-coupled neural networks with spike-synchronization-dependent plasticity rule: image segmentation and memristor circuit application. Neural Comput & Applic 32, 13441–13452 (2020). https://doi.org/10.1007/s00521-020-04752-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-04752-7

Keywords

Search

Navigation