Backpropagation through time: what it does and how to do it

Proceedings of the IEEE - Tập 78 Số 10 - Trang 1550-1560 - 1990
Paul J. Werbos1
1National Science Foundation, Washington, D. C., (USA)

Tóm tắt

Từ khóa


Tài liệu tham khảo

narendra, 1990, Neural Networks for Robotics and Control

10.1109/21.31036

10.1109/ICNN.1988.23866

10.1109/IJCNN.1989.118570

10.1007/BFb0006203

10.1016/0893-6080(88)90007-X

pineda, 1987, Generalization of backpropagation to recurrent and higher order networks, Proc IEEE Conf Neural Inform Processing Syst

almeida, 1987, A learning rule for asynchronous perceptrons with feedback in a combinatorial environment, Proc 1st IEEE Int Conf Neural Networks

10.1109/IJCNN.1989.118724

williams, 1990, Neural Networks for Robotics and Control

le cun, 1985, Une procedure d'apprentissage pour reseau a seuil assymetrique, Proc of COGNITIVA'85, 599

parker, 1985, Learning-logic

10.1109/IJCNN.1989.118682

watrous, 1987, Learning phonetic features using connectionist networks: an experiment in speech recognition, Proc 1st IEEE Int Conf Neural Networks

10.1109/IJCNN.1989.118584

nguyen, 1990, Neural Networks for Robotics and Control

rumelhart, 1986, Parallel Distributed Processing, 1, 10.7551/mitpress/5236.001.0001

werbos, 1974, Beyond Regression New Tools for Prediction and Analysis in the Behavioral Sciences

kawato, 1990, Neural Networks for Robotics and Control

werbos, 1987, Learning how the world works: Specifications for predictive networks in robots and brains, Proc 1987 IEEE Int Conf Syst Man Cybern

dennis, 1983, Numerical Methods for Unconstrained Optimization and Nonlinear Equations

10.1016/0893-6080(90)90088-3

shanno, 1990, Neural Networks for Robotics and Control

shanno, 1978, Conjugate-gradient methods with inexact searches, Math Oper Res, 3, 10.1287/moor.3.3.244