You need JavaScript to view this

Neural networks in front-end processing and control

Abstract

Research into neural networks has gained a large following in recent years. In spite of the long term timescale of this Artificial Intelligence research, the tools which the community is developing can already find useful applications to real practical problems in experimental research. One of the main advantages of the parallel algorithms being developed in AI is the structural simplicity of the required hardware implementation, and the simple nature of the calculations involved. This makes these techniques ideal for problems in which both speed and data volume reduction are important, the case for most front-end processing tasks. In this paper we illustrate the use of a particular neural network known as the Multi-Layer Perceptron as a method for solving several different tasks, all drawn from the field of Tokamak research. We also briefly discuss the use of the Multi-Layer Perceptron as a non-linear controller in a feedback loop. We outline the type of problem which can be usefully addressed by these techniques, even before the large-scale parallel processing hardware currently under development becomes cheaply available. We also present some of the difficulties encountered in applying these networks. (author) 13 figs., 9 refs.
Authors:
Lister, J B; Schnurrenberger, H; Staeheli, N; Stockhammer, N; Duperrex, P A; Moret, J M [1] 
  1. Ecole Polytechnique Federale, Lausanne (Switzerland). Centre de Recherche en Physique des Plasma (CRPP)
Publication Date:
Jul 01, 1991
Product Type:
Technical Report
Report Number:
LRP-430/91; CONF-9106122-
Reference Number:
SCA: 990301; PA: AIX-23:012758; SN: 92000638657
Resource Relation:
Conference: 7. international conference on real time computer applications in nuclear, particle and plasma physics,Juelich (Germany),18-28 Jun 1991; Other Information: DN: Invited paper presented at the 7. conference real time `91, at KFA Juelich, FRG, 24-28 Jun 1991.; PBD: Jul 1991
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; NEURAL NETWORKS; DATA PROCESSING; ACCURACY; ALGORITHMS; ARTIFICIAL INTELLIGENCE; CONTROL; EQUILIBRIUM PLASMA; FEEDBACK; GAUSS FUNCTION; IMAGE PROCESSING; LANGMUIR PROBE; SOFT X RADIATION; THEORETICAL DATA; TOKAMAK DEVICES; 990301; DATA HANDLING
OSTI ID:
10112240
Research Organizations:
Ecole Polytechnique Federale, Lausanne (Switzerland). Centre de Recherche en Physique des Plasma (CRPP)
Country of Origin:
Switzerland
Language:
English
Other Identifying Numbers:
Other: ON: DE92614099; TRN: CH9100594012758
Availability:
OSTI; NTIS (US Sales Only); INIS
Submitting Site:
CHN
Size:
9 p.
Announcement Date:
Feb 06, 1992

Citation Formats

Lister, J B, Schnurrenberger, H, Staeheli, N, Stockhammer, N, Duperrex, P A, and Moret, J M. Neural networks in front-end processing and control. Switzerland: N. p., 1991. Web.
Lister, J B, Schnurrenberger, H, Staeheli, N, Stockhammer, N, Duperrex, P A, & Moret, J M. Neural networks in front-end processing and control. Switzerland.
Lister, J B, Schnurrenberger, H, Staeheli, N, Stockhammer, N, Duperrex, P A, and Moret, J M. 1991. "Neural networks in front-end processing and control." Switzerland.
@misc{etde_10112240,
title = {Neural networks in front-end processing and control}
author = {Lister, J B, Schnurrenberger, H, Staeheli, N, Stockhammer, N, Duperrex, P A, and Moret, J M}
abstractNote = {Research into neural networks has gained a large following in recent years. In spite of the long term timescale of this Artificial Intelligence research, the tools which the community is developing can already find useful applications to real practical problems in experimental research. One of the main advantages of the parallel algorithms being developed in AI is the structural simplicity of the required hardware implementation, and the simple nature of the calculations involved. This makes these techniques ideal for problems in which both speed and data volume reduction are important, the case for most front-end processing tasks. In this paper we illustrate the use of a particular neural network known as the Multi-Layer Perceptron as a method for solving several different tasks, all drawn from the field of Tokamak research. We also briefly discuss the use of the Multi-Layer Perceptron as a non-linear controller in a feedback loop. We outline the type of problem which can be usefully addressed by these techniques, even before the large-scale parallel processing hardware currently under development becomes cheaply available. We also present some of the difficulties encountered in applying these networks. (author) 13 figs., 9 refs.}
place = {Switzerland}
year = {1991}
month = {Jul}
}