Have a personal or library account? Click to login

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.

Language: English
Page range: 107 - 112
Submitted on: Aug 26, 2019
Accepted on: Oct 7, 2019
Published on: Dec 16, 2019
Published by: Slovak University of Technology in Bratislava
In partnership with: Paradigm Publishing Services
Publication frequency: 2 issues per year

© 2019 Roman Budjač, Marcel Nikmon, Peter Schreiber, Barbora Zahradníková, Dagmar Janáčová, published by Slovak University of Technology in Bratislava
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.