Cellular Graph Grammar Encoding of Neural Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F11%3A43866584" target="_blank" >RIV/70883521:28140/11:43866584 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Cellular Graph Grammar Encoding of Neural Networks
Original language description
This paper presents a novel approach to neural network evolution. Genomes used in this evolution are based on well-described cellular encoding and a general mathematical idea of graph grammar. These genomes are optimized with genetic programming. This approach has been tested on the Iris flower data set to classify three iris flower species according to four measured quantities of each plant. Disadvantages and possible future improvements of this approach are listed in the end of the paper.
Czech name
—
Czech description
—

Project
<a href="/en/project/ED2.1.00%2F03.0089" target="_blank" >ED2.1.00/03.0089: The Centre of Security, Information and Advanced Technologies (CEBIA-Tech)</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

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

Article name in the collection
Annals of DAAAM for 2011 & Proceedings of the 22nd International DAAAM Symposium "Intelligent Manufacturing & Automation: Power of Knowledge and Creativity"
ISBN
978-3-901509-83-4
ISSN
1726-9679
e-ISSN
—
Number of pages
2
Pages from-to
1503-1504
Publisher name
DAAAM International Vienna
Place of publication
Vienna
Event location
Vienna
Event date
Nov 23, 2011
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)