You need JavaScript to view this

First experiments of parallel application in ENEA (Italian National Agency for New Technologies, Energy and the Environment): Neural networks; Note sui primi esperimenti di supercalcolo parallelo in ENEA: Le reti neurali

Abstract

In this report is presented a first experiment of a parallel application implemented on a Quadrics supercomputer in ENEA (Italian National Agency for New Technologies, Energy and the Environment). On this SIMD parallel machine it has been realized a learning algorithm for multilayer perceptrons, the so called backpropagation. This feasibility study has been aimed towards the solving of the problem of the logical exclusive or (XOR). The main reason being the nonlinear separability of such a problem, i.e. the need for a hidden layer in the neural architecture. The parallel algorithm is presented together with its performances under different optimizing techniques on Quadrics.
Authors:
Taraglio, S [1] 
  1. ENEA, Casaccia (Italy). Area Energia e Innovazione
Publication Date:
Nov 01, 1994
Product Type:
Technical Report
Report Number:
ENEA-RT-INN-94-41; RT/INN-94-41
Reference Number:
SCA: 990200; PA: ITA-95:000012; EDB-95:049422; SN: 95001347437
Resource Relation:
Other Information: PBD: Nov 1994
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; NEURAL NETWORKS; PARALLEL PROCESSING; ARTIFICIAL INTELLIGENCE; PROGRAMMING; ALGORITHMS; COMPUTER CODES; 990200; MATHEMATICS AND COMPUTERS
OSTI ID:
10123641
Research Organizations:
ENEA, Casaccia (Italy). Area Energia e Innovazione
Country of Origin:
Italy
Language:
Italian
Other Identifying Numbers:
Journal ID: ISSN 1120-5571; Other: ON: DE95749672; TRN: IT9500012
Availability:
OSTI; NTIS (US Sales Only)
Submitting Site:
ITA
Size:
14 p.
Announcement Date:
Jul 04, 2005

Citation Formats

Taraglio, S. First experiments of parallel application in ENEA (Italian National Agency for New Technologies, Energy and the Environment): Neural networks; Note sui primi esperimenti di supercalcolo parallelo in ENEA: Le reti neurali. Italy: N. p., 1994. Web.
Taraglio, S. First experiments of parallel application in ENEA (Italian National Agency for New Technologies, Energy and the Environment): Neural networks; Note sui primi esperimenti di supercalcolo parallelo in ENEA: Le reti neurali. Italy.
Taraglio, S. 1994. "First experiments of parallel application in ENEA (Italian National Agency for New Technologies, Energy and the Environment): Neural networks; Note sui primi esperimenti di supercalcolo parallelo in ENEA: Le reti neurali." Italy.
@misc{etde_10123641,
title = {First experiments of parallel application in ENEA (Italian National Agency for New Technologies, Energy and the Environment): Neural networks; Note sui primi esperimenti di supercalcolo parallelo in ENEA: Le reti neurali}
author = {Taraglio, S}
abstractNote = {In this report is presented a first experiment of a parallel application implemented on a Quadrics supercomputer in ENEA (Italian National Agency for New Technologies, Energy and the Environment). On this SIMD parallel machine it has been realized a learning algorithm for multilayer perceptrons, the so called backpropagation. This feasibility study has been aimed towards the solving of the problem of the logical exclusive or (XOR). The main reason being the nonlinear separability of such a problem, i.e. the need for a hidden layer in the neural architecture. The parallel algorithm is presented together with its performances under different optimizing techniques on Quadrics.}
place = {Italy}
year = {1994}
month = {Nov}
}