Advertisement

Analog Learning Neural Network Using Two-Stage Mode by Multiple and Sample Hold Circuits

  • Masashi Kawaguchi
  • Naohiro Ishii
  • Masayoshi Umeno
Conference paper
Part of the Studies in Computational Intelligence book series (SCI, volume 493)

Abstract

In the neural network field, many application models have been proposed. A neuro chip and an artificial retina chip are developed to comprise the neural network model and simulate the biomedical vision system. Previous analog neural network models were composed of the operational amplifier and fixed resistance. It is difficult to change the connection coefficient. In this study, we used analog electronic multiple and sample hold circuits. The connecting weights describe the input voltage. It is easy to change the connection coefficient. This model works only on analog electronic circuits. It can finish the learning process in a very short time and this model will enable more flexible learning.

Keywords

Electronic circuit neural network multiple circuit 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mead, C.: Analog VLSI and Neural Systems. Addison Wesley Publishing Company, Inc. (1989)Google Scholar
  2. 2.
    Chong, C.P., Salama, C.A.T., Smith, K.C.: Image-Motion Detection Using Analog VLSI. IEEE Journal of Solid-State Circuits 27(1), 93–96 (1992)CrossRefGoogle Scholar
  3. 3.
    Lu, Z., Shi, B.E.: Subpixel Resolution Binocular Visual Tracking Using Analog VLSI Vision Sensors. IEEE Transactions on Circuits and Systems-II: Analog and Digital Signal Processing 47(12), 1468–1475 (2000)Google Scholar
  4. 4.
    Saito, T., Inamura, H.: Analysis of a simple A/D converter with a trapping window. In: IEEE Int. Symp. Circuits Syst., pp. 1293–1305 (2003)Google Scholar
  5. 5.
    Luthon, F., Dragomirescu, D.: A Cellular Analog Network for MRF-Based Video Motion Detection. IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications 46(2), 281–293 (1999)CrossRefGoogle Scholar
  6. 6.
    Yamada, H., Miyashita, T., Ohtani, M., Yonezu, H.: An Analog MOS Circuit Inspired by an Inner Retina for Producing Signals of Moving Edges. Technical Report of IEICE, NC99-112, pp. 149–155 (2000)Google Scholar
  7. 7.
    Okuda, T., Doki, S., Ishida, M.: Realization of Back Propagation Learning for Pulsed Neural Networks Based on Delta-Sigma Modulation and Its Hardware Implementation. ICICE Transactions J88-D-II-4, 778–788 (2005)Google Scholar
  8. 8.
    Kawaguchi, M., Jimbo, T., Umeno, M.: Motion Detecting Artificial Retina Model by Two-Dimensional Multi-Layered Analog Electronic Circuits. IEICE Transactions E86-A-2, 387–395 (2003)Google Scholar
  9. 9.
    Kawaguchi, M., Jimbo, T., Umeno, M.: Analog VLSI Layout Design of Advanced Image Processing for Artificial Vision Model. In: IEEE International Symposium on Industrial Electronics, ISIE 2005 Proceeding, vol. 3, pp. 1239–1244 (2005)Google Scholar
  10. 10.
    Kawaguchi, M., Jimbo, T., Ishii, N.: Analog VLSI Layout Design and the Circuit Board Manufacturing of Advanced Image Processing for Artificial Vision Model. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds.) KES 2008, Part II. LNCS (LNAI), vol. 5178, pp. 895–902. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Kawaguchi, M., Jimbo, T., Umeno, M.: Dynamic Learning of Neural Network by Analog Electronic Circuits. In: Intelligent System Symposium, FAN 2010, S3-4-3 (2010)Google Scholar
  12. 12.
    Kawaguchi, M., Jimbo, T., Ishii, N.: Dynamic Learning of Neural Network by Analog Electronic Circuits. In: König, A., Dengel, A., Hinkelmann, K., Kise, K., Howlett, R.J., Jain, L.C. (eds.) KES 2011, Part IV. LNCS, vol. 6884, pp. 73–79. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Kawaguchi, M., Jimbo, T., Ishii, N.: Analog Learning Neural Network using Multiple and Sample Hold Circuits. In: IIAI/ACIS International Symposiums on Innovative E-Service and Information Systems, IEIS 2012, pp. 243–246 (2012)Google Scholar
  14. 14.
    Kawaguchi, M., Jimbo, T., Ishii, N.: Analog Real Time Learning Neural Network using Multiple and Sample Hold Circuits. In: Frontiers in Artificial Intelligence and Applications, vol. 243, pp. 1749–1757 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Masashi Kawaguchi
    • 1
  • Naohiro Ishii
    • 2
  • Masayoshi Umeno
    • 3
  1. 1.Department of Electrical & Electronic EngineeringSuzuka National College of TechnologyShirokoJapan
  2. 2.Department of Information ScienceAichi Institute of TechnologyYagusa-choJapan
  3. 3.Department of Electronic EngineeringChubu UniversityKasugaiJapan

Personalised recommendations