A Modified Invasive Weed Optimization Algorithm for Training of Feed-Forward Neural Networks
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F10%3A86081166" target="_blank" >RIV/61989100:27240/10:86081166 - isvavai.cz</a>
Výsledek na webu
<a href="http://dx.doi.org/10.1109/ICSMC.2010.5642265" target="_blank" >http://dx.doi.org/10.1109/ICSMC.2010.5642265</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICSMC.2010.5642265" target="_blank" >10.1109/ICSMC.2010.5642265</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
A Modified Invasive Weed Optimization Algorithm for Training of Feed-Forward Neural Networks
Popis výsledku v původním jazyce
Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than anothervery competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information
Název v anglickém jazyce
A Modified Invasive Weed Optimization Algorithm for Training of Feed-Forward Neural Networks
Popis výsledku anglicky
Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than anothervery competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
IN - Informatika
OECD FORD obor
—
Návaznosti výsledku
Projekt
—
Návaznosti
Z - Vyzkumny zamer (s odkazem do CEZ)
Ostatní
Rok uplatnění
2010
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
IEEE International Conference on Systems, Man, and Cybernetics, SMC 2010 : conference proceedings
ISBN
978-1-4244-6588-0
ISSN
1062-922X
e-ISSN
—
Počet stran výsledku
7
Strana od-do
3166 - 3173
Název nakladatele
IEEE
Místo vydání
345 E 47TH ST, NEW YORK, NY 10017 USA
Místo konání akce
Istanbul
Datum konání akce
10. 10. 2010
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
000295015303012