Title :
Robustness of recurrent neural networks against deformation of external input patterns
Author :
Gohara, Kazutoshi ; Yokoi, Kunio ; Uchikawa, Yoshiki
Author_Institution :
Sch. of Eng., Chubu Univ., Kasugai, Japan
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper describes experimental investigations into the robustness of recurrent neural networks against deformation of external input patterns. Three types of deformation are prepared to demonstrate robustness of the networks: 1) superposition of Gaussian white noise; 2) nonlinear expansion and contraction along time axis; and 3) combination of the first with the second. The response of the network used shows that desired outputs are obtained from the deformed input patterns
Keywords :
Gaussian noise; learning (artificial intelligence); recurrent neural nets; white noise; Gaussian white noise superposition; external input pattern deformation; nonlinear contraction; nonlinear expansion; recurrent neural networks; robustness; Boundary conditions; Cost function; Differential equations; Laboratories; Neurons; Noise robustness; Nonlinear dynamical systems; Recurrent neural networks; Supervised learning; White noise;
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
DOI :
10.1109/ICNN.1994.374315
