前馈神经网络中函数及其导数的逼近

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339) Pub Date : 1999-07-10 DOI:10.1109/IJCNN.1999.831531

E. Basson, A. Engelbrecht

引用次数: 15

摘要

提出了一种新的学习函数及其一阶导数的算法。利用梯度下降法与函数一起学习导数。初步结果表明，该算法能准确逼近导数。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Approximation of a function and its derivatives in feedforward neural networks

A new learning algorithm is presented that learns a function and its first-order derivatives. Derivatives are learned together with the function using gradient descent. Preliminary results show that the algorithm accurately approximates the derivatives.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)

自引率

0.00%

发文量