<abstract xmlns="http://www.w3.org/1999/xhtml"><p>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.</p></abstract>

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.

Automated Machine Learning Overview

Slovak University of Technology in Bratislava

Faculty of Materials Science and Technology in Trnava, Institute of Applied Informatics, Automation and Mechatronics

Faculty of Applied Informatics, Department of Automation and Control Engineering

Research Papers Faculty of Materials Science and Technology Slovak University of Technology

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Automated Machine Learning Overview"}

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...

Automated Machine Learning Overview

Publié en ligne: 16 déc. 2019

Pages: 107 - 112

Reçu: 26 août 2019

Accepté: 07 oct. 2019

DOI: https://doi.org/10.2478/rput-2019-0033

Mots clés
Neural networks, auto-machine learning, deep neural network

© 2019 Roman Budjač et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Automated Machine Learning Overview

Publié en ligne: 16 déc. 2019

Pages: 107 - 112

Reçu: 26 août 2019

Accepté: 07 oct. 2019

DOI: https://doi.org/10.2478/rput-2019-0033

Mots clésNeural networks, auto-machine learning, deep neural network

© 2019 Roman Budjač et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
Neural networks, auto-machine learning, deep neural network