본문 바로가기
  • Home

A Study on MRD Methods of A RAM-based Neural Net

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2009, 14(9), pp.11-19
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

이동형 1 Seongjin Kim 2 박상무 3 LEE SOO DONG 2 ChoelYoung Ock 2

1한국폴리텍VII대학 울산캠퍼스
2울산대학교
3영산대학교

Accredited

ABSTRACT

A RAM-based Neural Net(RBNN) which has multi-discriminators is more effective than RBNN with a discriminator. Experience Sensitive Cumulative Neural Network and 3-D Neuro System (3DNS) that accumulate the features point improved the performance of BNN, which were enabled to train additional and repeated patterns and extract a generalized pattern. In recognition process of Neural Net with multi-discriminator, the selection of class was decided by the value of MRD which calculates the accumulated sum of each class. But they had a saturation problem of its memory cells caused by learning volume increment. Therefore, the decision of MRD has a low performance because recognition rate is decreased by saturation. In this paper, we propose the method which improve the MRD ability. The method consists of the optimum MRD and the matching ratio prototype to generalized image, the cumulative filter ratio, the gap of prototype response MRD. We experimented the performance using MNIST database of NIST without preprocessor, and compared this model with 3DNS. The proposed MRD method has more performance of recognition rate and more stable system for distortion of input pattern than 3DNS.

Citation status

* References for papers published after 2022 are currently being built.