This paper presents a recurrent neural network model which takes outputs of a hidden layer of multilayer neural network (MNN) as inputs. The proposed network model has a context layer for taking input streams out of the hidden layer. We have proved that the proposed recurrent neural network (RNN) model should be a generalized form of nonlinear autoregressive moving average (NARMA) model. We have tested performances of the proposed method for a few time series data. The prediction performances of the recurrent neural network model are shown to be competitive enough for a general predictor.
목차
I. 서론 1. 연구배경 2. 연구목적 II. 연구모형 및 방법 1. 시계열 예측 모형 (Time Series Prediction Models) 2. 통계적 시계열모형과 신경망 시계열모형 III. 실험결과의 분석 IV. 결론 참고문헌 ABSTRACT