한국지능시스템학회:학술대회논문집 (Proceedings of the Korean Institute of Intelligent Systems Conference)
- 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
- /
- Pages.118-121
- /
- 1998
REVISING THE TRADITIONAL BACKPROPAGATION WITH THE METHOD OF VARIABLE METRIC(QUASI-NEWTON) AND APPROXIMATING A STEP SIZE
- Choe, Sang-Woong (Dept. of Management Information System , Pohang Junior College) ;
- Lee, Jin-Choon (Dept. of Industrial Engineering, Kyungil University)
- 발행 : 1998.06.01
초록
In this paper, we propose another paradigm(QNBP) to be capable of overcoming Limitations of the traditional backpropagation(SDBP). QNBPis based on the method of Quasi -Newton(variable metric) with the nomalized direction vectors and computes step size through the linear search. Simulation results showed that QNBP was definitely superior to both the stochasitc SDBP and the deterministic SDBP in terms of accuracy and rate of convergence and might sumount the problem of local minima. and there was no different between DFP+SR1 and BFGS+SR1 combined algrothms in QNBP.
키워드