Classification with Extreme Learning Machine on GPU
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F15%3A86096068" target="_blank" >RIV/61989100:27240/15:86096068 - isvavai.cz</a>
Alternative codes found
RIV/61989100:27740/15:86096068
Result on the web
<a href="http://dx.doi.org/10.1109/INCoS.2015.30" target="_blank" >http://dx.doi.org/10.1109/INCoS.2015.30</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/INCoS.2015.30" target="_blank" >10.1109/INCoS.2015.30</a>
Alternative languages
Result language
angličtina
Original language name
Classification with Extreme Learning Machine on GPU
Original language description
The general classification is a machine learning task that tries to assign the best class to a given unknown input vector based on past observations (training data). Most of developed algorithms are very time consuming for large datasets (Support VectorMachine, Deep Neural Networks, etc.). Extreme Learning Machine (ELM) is a high quality classification algorithm that gains much popularity in recent years. This paper shows that the speed of learning of this algorithm may be improved by using GPU platform. Experimental results showed that proposed approach is much faster and provides the same accuracy as the original ELM algorithm. The proposed approach runs completely on GPU platform and thus it may be effectively incorporated within other applications.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/ED1.1.00%2F02.0070" target="_blank" >ED1.1.00/02.0070: IT4Innovations Centre of Excellence</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Intelligent Networking and Collaborative Systems INCoS-2015 : 7th International Conference : proceedings : September 2-4, 2015, Taipei, Tchaj-wan
ISBN
978-1-4673-7694-5
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
116-122
Publisher name
IEEE
Place of publication
Danvers
Event location
Taipei
Event date
Sep 2, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—