Backpropagation through time for a general class of recurrent network

被引：13

作者：

De Jesús, O ^{[1
]}

Hagan, MT ^{[1
]}

机构：

[1] Oklahoma State Univ, Sch Elect & Comp Engn, Stillwater, OK 74078 USA

来源：

IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS | 2001年

关键词：

D O I：

10.1109/IJCNN.2001.938786

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper introduces a general class of dynamic network the Layered Digital Dynamic Network. It then derives the backpropagation-through-time algorithm for computing the gradient of the network error with respect to the weights of the network.

引用

页码：2638 / 2643

页数：6

共 8 条

[1]

De Jesus O, 2001, INT JOINT C NEUR NET

[2]

DEMUTH HB, 2000, USERS GUIDE NEURAL N

[3]

Hagan MT., 1996, NEURAL NETWORK DESIG

[4]

Magnus J., 1999, Matrix Differential Calculus with Applications in Statistic and Econometrics

[5]

Narendra K S, 1990, IEEE Trans Neural Netw, V1, P4, DOI 10.1109/72.80202

[6] BACKPROPAGATION THROUGH TIME - WHAT IT DOES AND HOW TO DO IT [J].

WERBOS, PJ .

PROCEEDINGS OF THE IEEE, 1990, 78 (10) :1550-1560

[7]

YANG W, 1994, THESIS OKLAHOMA STAT

[8]

YANG W, 1993, P 7 OKL S ART INT ST, P226

← 1 →