Adaptive behavior with fixed weights in RNN: An overview

被引:32
作者
Prokhorov, DV [1 ]
Feldkamp, LA [1 ]
Tyukin, IY [1 ]
机构
[1] Ford Res Lab, Dearborn, MI 48121 USA
来源
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年
关键词
D O I
10.1109/IJCNN.2002.1007449
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we review recent results on adaptive behavior attained with fixed-weight recurrent neural networks (meta-learning). We argue that such behavior is a natural consequence of prior training.
引用
收藏
页码:2018 / 2022
页数:3
相关论文
共 11 条
[1]  
BACK A, 1997, P ICONIP
[2]  
FELDKAMP L, 1996, P IEEE INT C NEUR NE
[3]   A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification [J].
Feldkamp, LA ;
Puskorius, GV .
PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2259-2277
[4]  
Feldkamp LA, 1997, 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, P2268, DOI 10.1109/ICNN.1997.614397
[5]  
FELDKAMP LA, 2001, P 11 YAL WORKSH AD L, P78
[6]  
Hochreiter S, 2001, LECT NOTES COMPUT SC, V2130, P87
[7]  
Kolen J.F., 2010, FIELD GUIDE DYNAMICA, DOI [10.1109/9780470544037.ch14, DOI 10.1109/9780470544037.CH14]
[8]  
Lo JT, 2001, IEEE IJCNN, P1279, DOI 10.1109/IJCNN.2001.939545
[9]  
Prokhorov D., 2001, FIELD GUIDE DYNAMICA
[10]  
Younger AS, 2001, IEEE IJCNN, P2001, DOI 10.1109/IJCNN.2001.938471