Evolution Strategies for Deep Neural Network Models Design

0478624 - ÚI 2018 RIV DE eng C - Konferenční příspěvek (zahraniční konf.)
Vidnerová, Petra - Neruda, Roman
Evolution Strategies for Deep Neural Network Models Design.
Proceedings ITAT 2017: Information Technologies - Applications and Theory. Aachen & Charleston: Technical University & CreateSpace Independent Publishing Platform, 2017 - (Hlaváčová, J.), s. 159-166. CEUR Workshop Proceedings, V-1885. ISBN 978-1974274741. ISSN 1613-0073.
[ITAT 2017. Conference on Theory and Practice of Information Technologies - Applications and Theory /17./. Martinské hole (SK), 22.09.2017-26.09.2017]
Grant CEP: GA ČR GA15-18108S
Grant ostatní: GA MŠk(CZ) LM2015042
Institucionální podpora: RVO:67985807
Klíčová slova: deep neural networks * evolution strategies * architecture optimisation * Keras
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://ceur-ws.org/Vol-1885/159.pdf

Deep neural networks have become the state-of art methods in many fields of machine learning recently. Still, there is no easy way how to choose a network architecture which can significantly influence the network performance. This work is a step towards an automatic architecture design. We propose an algorithm for an optimization of a network architecture based on evolution strategies. The algorithm is inspired by and designed directly for the Keras library [3] which is one of the most common implementations of deep neural networks. The proposed algorithm is tested on MNIST data set and the prediction of air pollution based on sensor measurements, and it is compared to several fixed architectures and support vector regression.
Trvalý link: http://hdl.handle.net/11104/0274767