類神經網路於非線性函數近似之應用

Artificial Neural Network Approaches for Nonlinear Function Approximation

郭信川(H. C. Kuo) ； 陳彥名(Y. M. Chen)

《中國造船暨輪機工程學刊》 21卷4期 (2002/11) Pp. 231-238

https://doi.org/10.29982/JTSNAME.200211.0003

摘要

類神經網路方法對資訊系統的輸入與輸出映射的近似能力，近年來相當受注目，且廣泛用於各領域。本文對類神經網路方法中，最成熟的一種模式－倒傅遞網路法，探討對非線性函數問題的輸入與輸出問題之映射能力。文中以三個非線性函數例加以測試，並檢討其架構參數對映射能力之影響;亦即評估對於非線性函數的辨識或近似能力之影響。

關鍵字

類神經網路 ； 快速倒傳遞演算法 ； 非線性函數 ； 多層感知機

並列摘要

Neural networks have recently received much attention due to their universal approximation capabilities. In other words, neural networks can identify and learn correlated patterns between sets of input data and corresponding target values. Among the many existing artificial neural network paradigms, the back-propagation network (BPN) is most widely used network for several applications. In this paper, the BPN is used to deal with identifying and approximating some nonlinear functions. Finally, effects of some parameters in the structure of a multi-layer perceptron such as number of hidden layers and neurons in each hidden layer on the performance of training back-propagation network are also examined and discussed.

並列關鍵字

Neural Networks ； Quick-Back-Propagation ； Nonlinear Function ； Multi-layer Perceptron