Neuromorphic learning of continuous-valued mappings from noise-corrupted data

Author

Troudet, T. ; Merrill, W.

Author_Institution

Sverdrup Technol., Brook Park, OH, USA

Volume

2

Issue

2

fYear

1991

fDate

3/1/1991 12:00:00 AM

Firstpage

294

Lastpage

301

Abstract

The effect of noise on the learning performance of the backpropagation algorithm is analyzed. A selective sampling of the training set is proposed to maximize the learning of control laws by backpropagation, when the data have been corrupted by noise. The training scheme is applied to the nonlinear control of a cart-pole system in the presence of noise. The neural computation provides the neurocontroller with good noise-filtering properties. In the presence of plant noise, the neurocontroller is found to be more stable than the teacher. A novel perspective on the application of neural network technology to control engineering is presented

Keywords

learning systems; neural nets; nonlinear control systems; backpropagation; cart-pole system; continuous-valued mappings; control engineering; learning systems; neural network; neurocontroller; neuromorphic learning; noise-corrupted data; nonlinear control; Algorithm design and analysis; Backpropagation algorithms; Control engineering; Control systems; Neural networks; Neurocontrollers; Neuromorphics; Nonlinear control systems; Performance analysis; Sampling methods;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.80340

Filename

80340