Evolving Keras Architectures for Sensor Data Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F17%3A00478496" target="_blank" >RIV/67985807:_____/17:00478496 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.15439/2017F241" target="_blank" >http://dx.doi.org/10.15439/2017F241</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.15439/2017F241" target="_blank" >10.15439/2017F241</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evolving Keras Architectures for Sensor Data Analysis

Popis výsledku v původním jazyce

Deep neural networks enjoy high interest and have become the state-of-art methods in many fields of machine learning recently. Still, there is no easy way for a choice of network architecture. However, the choice of architecture can significantly influence the network performance. This work is the first step towards an automatic architecture design. We propose a genetic algorithm for an optimization of a network architecture. The algorithm is inspired by and designed directly for the Keras library [1] that is one of the most common implementations of deep neural networks. The target application is the prediction of air pollution based on sensor measurements. The proposed algorithm is evaluated on experiments on sensor data and compared to several fixed architectures and support vector regression.

Název v anglickém jazyce

Evolving Keras Architectures for Sensor Data Analysis

Popis výsledku anglicky

Deep neural networks enjoy high interest and have become the state-of-art methods in many fields of machine learning recently. Still, there is no easy way for a choice of network architecture. However, the choice of architecture can significantly influence the network performance. This work is the first step towards an automatic architecture design. We propose a genetic algorithm for an optimization of a network architecture. The algorithm is inspired by and designed directly for the Keras library [1] that is one of the most common implementations of deep neural networks. The target application is the prediction of air pollution based on sensor measurements. The proposed algorithm is evaluated on experiments on sensor data and compared to several fixed architectures and support vector regression.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA15-18108S" target="_blank" >GA15-18108S: Modelová složitost neuronových, radiálních a jádrových sítí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 2017 Federated Conference on Computer Science and Information Systems

ISBN

978-83-946253-7-5

ISSN

2300-5963

e-ISSN

—

Počet stran výsledku

4

Strana od-do

109-112

Název nakladatele

Polish Information Processing Society

Místo vydání

Warszawa

Místo konání akce

Prague

Datum konání akce

3. 9. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000417412800015