Neural Network Synthesis via Asynchronous Analytic Programming

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F11%3A43867262" target="_blank" >RIV/70883521:28140/11:43867262 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Neural Network Synthesis via Asynchronous Analytic Programming
Original language description
This article deals with Analytic Programming (AP) which was proven to be highly effective tool of Artificial Neural Network (ANN) synthesis and optimization. New innovative asynchronous distribution of Self-Organizing Migration Algorithm (SOMA) is introduced and used together with AP. Such implementation can for example save 67% of computation time if distributed between 8 processors. Efficiency of AP as well as asynchronous distribution of SOMA was tested and statistically measured on 921937 evaluations, each of them containing another separate execution of SOMA.
Czech name
—
Czech description
—

Project
<a href="/en/project/2C06007" target="_blank" >2C06007: Intelligent approach to energetic system control of urban agglomeration.</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
12th WSEAS International Conference on Neural Networks, Fuzzy Systems, Evolutionary Computing & Automation
ISBN
978-960-474-292-9
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
92-97
Publisher name
WSEAS press
Place of publication
Timisoara
Event location
Brasov
Event date
Apr 11, 2011
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)