DocumentCode
288778
Title
The inverse method for recurrent neural networks
Author
Hatano, Shoji ; Sato, Yuji ; Hatano, Hisaaki ; Furuya, Tatsumi
Author_Institution
Real World Comput. Partnership, Ibaraki, Japan
Volume
5
fYear
1994
fDate
27 Jun-2 Jul 1994
Firstpage
3122
Abstract
Investigates the inverse method for recurrent neural networks. The inverse method calculates an input of a network that locally minimizes the least-mean-square error between a given output and an output from the network. The authors compare this method with: differential algorithm, BP, bounded BP, valley searching, and bounded valley searching. The authors´ experiments show that the inverse method gets better desired inputs by using bounded algorithms than by the other
Keywords
backpropagation; function approximation; inverse problems; least mean squares methods; recurrent neural nets; search problems; bounded valley searching; differential algorithm; inverse method; least-mean-square error; recurrent neural networks; Computer networks; Equations; Error correction; Inverse problems; Kinematics; Multi-layer neural network; Neural networks; Neurons; Recurrent neural networks; Robots;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location
Orlando, FL
Print_ISBN
0-7803-1901-X
Type
conf
DOI
10.1109/ICNN.1994.374732
Filename
374732
Link To Document