DOI QR코드

DOI QR Code

Recognition of the Korean Alphabet using Phase Synchronization of Neural Oscillator

  • 발행 : 2004.02.01

초록

Neural oscillator can be applied to oscillatory systems such as analyses of image information, voice recognition and etc. Conventional EBPA (Error back Propagation Algorithm) is not proper for oscillatory systems with the complicate input`s patterns because of its tedious training procedures and sluggish convergence problems. However, these problems can be easily solved by using a synchrony characteristic of neural oscillator with PLL(Phase Locked Loop) function and by using a simple Hebbian learning rule. Therefore, in this paper, a technique for Recognition of the Korean Alphabet using Phase Synchronized Neural Oscillator was introduced.

키워드

참고문헌

  1. Hoppensteadt F.C. and Izhikevich E.M., "Pattern Recognition via Synchronization in PLL Neural Networks", IEEE Trans. on NN, Vol.11, No. 3, pp.734-738,2000 https://doi.org/10.1109/72.846744
  2. Hoppensteadt F.C. and Izhikevich E.M., "Oscillatory Neuro-computers with Dynamic Connectivity", PhysIcal Revjew Letters, Vol.82, pp.2983-2986, 1999 https://doi.org/10.1103/PhysRevLett.82.2983
  3. Dorel M. Sala and Krzysztof J. Cios, "Solving Graph Algorithms with Networks of Spiking Neurons" , IEEE Trans, Vol.10, No.4, 1999
  4. M. Rosenblum, A.Pikovsky and etc, "Phase Synchronization: From Theory to Data Analysis", Preprint submitted to Elsevier Preprint, pp.1-46, 1999
  5. Abhijit S. Pandya and Robert B.Macy, "Pattern Recognition with Neural Networks in C+ +", CRC PRESS., 1995
  6. Schalkoff Robert J., "Pattern Recognition", John Wiley & Sons, 1992
  7. Eugene M. Izhikevich, "Class 1 Neural Excitability, Conventional Synapses, Weakly Connected Networks, and Mathematical Foundations of Pulse-Coupled Models.", IEEE Trans. On Neural Networks,Vol. 10, pp.499-507, 1999 https://doi.org/10.1109/72.761707
  8. Pao. YohHan, "Adaptive Pattern Recognition and Neural Networks", Addison Wesley Press, 1989