AUTOMATED MACHINE LEARNING OVERVIEW
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F19%3A63524121" target="_blank" >RIV/70883521:28140/19:63524121 - isvavai.cz</a>
Result on the web
<a href="https://content.sciendo.com/view/journals/rput/27/45/article-p107.xml" target="_blank" >https://content.sciendo.com/view/journals/rput/27/45/article-p107.xml</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.2478/rput-2019-0033" target="_blank" >10.2478/rput-2019-0033</a>
Alternative languages
Result language
angličtina
Original language name
AUTOMATED MACHINE LEARNING OVERVIEW
Original language description
This paper aims at deeper exploration of the new field named auto-machine learning, as it shows promising results in specific machine learning tasks e.g. image classification. The following article is about to summarize the most successful approaches now available in the A.I. community. The automated machine learning method is very briefly described here, but the concept of automated task solving seems to be very promising, since it can significantly reduce expertise level of a person developing the machine learning model. We used Auto-Keras to find the best architecture on several datasets, and demonstrated several automated machine learning features, as well as discussed the issue deeper
Czech name
—
Czech description
—
Classification
Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Research Papers Faculty of Materials Science and Technology Slovak University of Technology
ISSN
1338-0532
e-ISSN
—
Volume of the periodical
27
Issue of the periodical within the volume
45
Country of publishing house
SK - SLOVAKIA
Number of pages
6
Pages from-to
107-112
UT code for WoS article
—
EID of the result in the Scopus database
—