Prediction of Nonlinear Sequences by Self-Organized CMAC Neural Network

자율조직 CMAC 신경망에 의한 비선형 시계열 예측

  • 이태호 (울산대학교 전기전자정보시스템공학부)
  • Published : 2002.10.01

Abstract

An attempt of using SOCMAC neural network for the prediction of a nonlinear sequence, which is generated by Mackey-Glass equation, is reported. The ,report shows the SOCMAC can handle a system with multi-dimensional continuous inputs, which has been considered very difficult, if not impossible, task to be implemented by a CMAC neural network because of a huge amount of memory required. Also, an improved training method based on the variable receptive fields is proposed. The Performance ranged somewhere around those of TDNN and BP neural networks.

SOCMAC 신경망에 의하여 Mackey-Glass의 비선형 시계열 예측을 시도하였다 다차원 연속 입력 변수를 가지는 문제는 요구되는 기억용량의 규모가 너무 커서 CMAC에서는 일반적으로 취급이 곤난한 대상이었으나 SOCMAC에서는 이것이 가능함을 보였다. 또한 학습과정에서 수용영역(receptive field)을 가변으로 하는 개선된 방법을 제시하였다. 예측오차는 TDNN(time-delayed neural network)이나 BP(back-propagation) 수준이었다.

Keywords

References

  1. Proceedings of the IEEE International Conference on Industrial Technology, 1994 A Self-Organized CMAC Controller Chow, M.;Menzzi, A.
  2. IECON' 97. 23rd International Conference on Industrial Electronics, Control and Instrumentation v.3 On the training of a multi-resolution CMAC neural network Chow, M.;Menzzi, A.
  3. Transactions of ASME Series G, Journal of Dynamic Systems, Measurement and Control v.97 A new approach to manipulator control: the Cerebella Model Articulation Controller(CMAC) Albus, J. S.
  4. Proceedings of the 2000 IEEE International Symposium on Intelligent Control Two suggestions for efficient implementation of CMAC's Benavent, X.;Domingo, J.;Vegara, F.;Pelechano, J.
  5. Proceedings. IJCNN '01. International Joint Conference on Neural Networks v.3 A self-organizing HCMAC neural network classifier Lee, H.;Chen, C.;Lu, Y.
  6. Proceedings of the IEEE v.86 no.11 Local dynamic modeling with self-organizing maps and applications to nonlinear system identification and control Principe, J. C.;Wang, L.;Motter, M. A.
  7. Proceedings of International Conference on Intelligent System Applocation to Power Systems Application of CMAC for Short-Term Load Forcasting Lee, T.;Lee, K. Y.
  8. Second IEEE International Conference on Fuzzy Systems v.2 Predicting chaotic time series with fuzzy if-then rules Jang, J.-S.R.;Sun, C.-T.
  9. Journal of Electrical Eng. and Information Science v.4 no.1 Time-Delayed Recurrent Neural Network for Temporal Correlations and Prediction, ans its Application to Phone Recognition Kim, S. S.(et al)
  10. IEEE Transactions on Fuzzy Systems v.9 no.6 Powerful and Flexible Fuzzy Algorithm for Nonlinear Dynamic System Identification Lo Schiavo, A.;Luciano A. M.