@article{ART001914282},
author={Kim, Kwang-baek and Park Choong Shik},
title={A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2014},
volume={19},
number={9},
pages={33-38}
TY - JOUR
AU - Kim, Kwang-baek
AU - Park Choong Shik
TI - A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control
JO - Journal of The Korea Society of Computer and Information
PY - 2014
VL - 19
IS - 9
PB - The Korean Society Of Computer And Information
SP - 33
EP - 38
SN - 1598-849X
AB - The FCM based hybrid RBF network is a heterogeneous learning network model that appliesFCM algorithm between input and middle layer and applies Max_Min algorithm between middlelayer and output. The Max-Min neural network uses winner nodes of the middle layer as input butshows inefficient learning in performance when the input vector consists of too many patterns. To overcome this problem, we propose a dynamic learning rate control based on fuzzy logic. Theproposed method first classifies accurate/inaccurate class with respect to the difference betweentarget value and output value with threshold and then fuzzy membership function and fuzzydecision logic is designed to control the learning rate dynamically. We apply this proposed RBFnetwork to the character recognition problem and the efficacy of the proposed method is verifiedin the experiment.
KW - FCMbased hybrid network;Max-Min neural network;Fuzzy logic;Learning rate
DO -
UR -
ER -
Kim, Kwang-baek and Park Choong Shik. (2014). A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control. Journal of The Korea Society of Computer and Information, 19(9), 33-38.
Kim, Kwang-baek and Park Choong Shik. 2014, "A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control", Journal of The Korea Society of Computer and Information, vol.19, no.9 pp.33-38.
Kim, Kwang-baek, Park Choong Shik "A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control" Journal of The Korea Society of Computer and Information 19.9 pp.33-38 (2014) : 33.
Kim, Kwang-baek, Park Choong Shik. A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control. 2014; 19(9), 33-38.
Kim, Kwang-baek and Park Choong Shik. "A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control" Journal of The Korea Society of Computer and Information 19, no.9 (2014) : 33-38.
Kim, Kwang-baek; Park Choong Shik. A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control. Journal of The Korea Society of Computer and Information, 19(9), 33-38.
Kim, Kwang-baek; Park Choong Shik. A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control. Journal of The Korea Society of Computer and Information. 2014; 19(9) 33-38.
Kim, Kwang-baek, Park Choong Shik. A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control. 2014; 19(9), 33-38.
Kim, Kwang-baek and Park Choong Shik. "A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control" Journal of The Korea Society of Computer and Information 19, no.9 (2014) : 33-38.