A Study on the Digital Implementation of Multi-layered Neural Networks for Pattern Recognition

패턴인식을 위한 다층 신경망의 디지털 구현에 관한 연구

  • 박영석 (경남대학교 정보통신공학부)
  • Published : 2001.04.01

Abstract

In this paper, in order to implement the multi-layered perceptron neural network using pure digital logic circuit model, we propose the new logic neuron structure, the digital canonical multi-layered logic neural network structure, and the multi-stage multi-layered logic neural network structure for pattern recognition applications. And we show that the proposed approach provides an incremental additive learning algorithm, which is very simple and effective.

본 연구에서는 패턴 인식용 다층 퍼셉트론 신경망을 순수 디지털 논리회로 모델로 구현할 수 있도록 새로운 논리뉴런의 구조, 디지털 정형 다층논리신경망 구조, 그리고 패턴인식의 응용을 위한 다단 다층논리 신경망 구조를 제안하고, 또한 제안된 구조는 매우 단순하면서도 효과적인 증가적인 가법적(Incremental Additive) 학습알고리즘이 존재함을 보였다.

Keywords

References

  1. Neural Network a Comprehensive Foundation S. Haykin
  2. Neurocomputing - Paper Collections I. A. Anderson
  3. VLSI for Pattern Recognition and Image Processing King-sun Fu
  4. IEEE Circuits and Devices Mag. Neural Networks in CMOS: A Case Study A. Masaki;Y. Hirai;M. Yamada
  5. System Data Book Aptix Inc.
  6. The Programmable Gate Array Data Book Xilinx Inc.
  7. IEEE Trans. ASSP v.36 Layered Neural Nets for Pattern Recognition B. Windrow;R. G. Winter;R. A. Baxter
  8. Discrete Neural Computation: A Theoretical Foundation Kai-Yeung Siu;V. Roychowdhury;T. Kailath
  9. Adaptive Pattern Recognition and Neural Networks Yoh-Han Pao
  10. 문자인식: 이론과 실제 v.1;2 이성환