Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Learning for Environment and Behavior Pattern Using Recurrent Modular Neural Network Based on Estimated Emotion

감정평가에 기반한 환경과 행동패턴 학습을 위한 궤환 모듈라 네트워크

  • 김성주 (중앙대학교 일반대학원 전자전기공학부) ;
  • 최우경 (중앙대학교 일반대학원 전자전기공학부) ;
  • 김용민 (충청대학 컴퓨터학부) ;
  • 전홍태 (중앙대학교 일반대학원 전자전기공학부)
  • Published : 2004.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Rational sense is affected by emotion. If we add the factor of estimated emotion by environment information into robots, we may get more intelligent and human-friendly robots. However, various sensory information and pattern classification are prescribed for robots to learn emotion so that the networks are suitable for the necessity of robots. Neural network has superior ability to extract character of system but neural network has defect of temporal cross talk and local minimum convergence. To solve the defects, many kinds of modular neural networks have been proposed because they divide a complex problem into simple several subproblems. The modular neural network, introduced by Jacobs and Jordan, shows an excellent ability of recomposition and recombination of complex work. On the other hand, the recurrent network acquires state representations and representations of state make the recurrent neural network suitable for diverse applications such as nonlinear prediction and modeling. In this paper, we applied recurrent network for the expert network in the modular neural network structure to learn data pattern based on emotional assessment. To show the performance of the proposed network, simulation of learning the environment and behavior pattern is proceeded with the real time implementation. The given problem is very complex and has too many cases to learn. The result will show the performance and good ability of the proposed network and will be compared with the result of other method, general modular neural network.

감정은 지능을 지닌 존재의 이성판단에 영향을 준다. 그래서 주변 환경정보에 의해 평가된 기본적이고 보편적인 감정을 로봇에 가미하면 더욱 인간과 가까운 지능 로봇이 될 것이다. 그러나 인간의 감정을 학습하기 위해서는 다양한 감각정보의 학습과 패턴 분류가 선행되어야 하고 이를 위해서 적합한 네트워크 구조가 요구된다. 신경망은 시스템의 특징을 추출하는데 매우 우수한 능력을 발휘하고 있다. 그러나 임시적 혼선현상과 지역 최소치에 수렴하는 단점이 있다. 그래서 복잡한 문제를 단순한 여러 개의 부분적인 문제로 나누어 해결하는 모듈라 설계방법이 관심의 대상이 되고 있다. 본 논문에서는 수많은 감정평가와 학습 데이터 패턴들을 학습하기 위해서 재결합과 재구성에 탁월한 성능을 지닌 Jacobs와 Jordan이 제안한 모듈라 네트워크와 상황의 재 표현이 가능하고 예측값과 모델링에 적합한 특징을 지닌 궤환 신경망을 결합하였다. 구성된 구조는 기존의 모듈라 네트워크의 학습결과와 비교 검토하였다.

Keywords

References

  1. Simon Haykin, Neural Networks - A Comprehensive Foundation, Macmillian college Publishing company Inc., 1994.
  2. Chin-Teng Lin and C. S. George Lee, Neural Fuzzy Systems - A Neuro Fuzzy Synergism to intelligent System, Prentice Hall PTR, 1996.
  3. 강훈,심귀보, 지능정보 시스템, 대영사, 2000.
  4. Jacek M. Zurada, Introduction to Artificial Neural System, West Publishing Company, 1992.
  5. Gasser Auda and M. Kamel, "Modular neural networks : A survey", Int. Journal of Neural Systems, Vol. 9, No. 2, pp 129-151, 1999. https://doi.org/10.1142/S0129065799000125
  6. Tomas Hrycej, Modular Learning in Neural Network, John Wiley & Sons Inc., 1992.
  7. Gasser Auda and Mohamed Kamel, "Modular neural networks Classifier: A Comparative Study", Journal of Intelligent and Robotic Systems, Vol. 21, pp 117-129, 1998. https://doi.org/10.1023/A:1007925203918
  8. R. A. Jacobs, M. I. Jordan, S. J. Nowlan, and G. E. Hinton, "Adaptive Mixtures of Local Experts", Neural Computation, Vol. 6., pp. 181-214, 1994. https://doi.org/10.1162/neco.1994.6.2.181
  9. Sung-Bae Cho, "Evolutionary Modular Neural Networks for Intelligent Systems", International Journal of Intelligent Systems, Vol. 13, pp. 483-493, 1998. https://doi.org/10.1002/(SICI)1098-111X(199806)13:6<483::AID-INT4>3.0.CO;2-H
  10. G. Aada and M. Kamel, "CMNN: Cooperative Modular Neural Networks for pattern recognition", Pattern Recognition Letters, Vol. 18, pp. 11-13, 1997.
  11. Ke Chen, Liping Yang, Xiang Yu and Huisheng Chi, "A self-generating modular neural network architecture for supervised learning", Neurocomputing, Vol. 16, pp. 33-48, 1997. https://doi.org/10.1016/S0925-2312(96)00057-4
  12. Gasser Auda, Mohamed Kamel and Hazem Raafat, "Modular Neural Network for Classifier", IEEE Trans. on Neural Network, pp. 1279-1284, 1996.
  13. Michael I. Jordan and Robert A. Jacobs, "Hierarchical Mixtures of Experts and the EM Algorithm", Neural computation, Vol. 6, No. 1, pp. 181-214, 1994. https://doi.org/10.1162/neco.1994.6.2.181
  14. Chin-Teng Lin and C. S. George Lee, Neural Fuzzy Systems - A Neuro-Fuzzy Synergism to Intelligent Systems, A Simon & Schuster Company, 1996.
  15. Steve Lawrence, C. Lee Giles and Sandiway Fong, "Natural Language Grammatical Inference with Recurrent Neural Networks", IEEE Trans. on Knowledge and Data engineering, Vol. 12, No. 1, pp. 126-140, 2000. https://doi.org/10.1109/69.842255