Genetic Algorithm for Automatic tuning of neural network hyperparameters
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F63839172%3A_____%2F18%3A10133127" target="_blank" >RIV/63839172:_____/18:10133127 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1117/12.2304955" target="_blank" >http://dx.doi.org/10.1117/12.2304955</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1117/12.2304955" target="_blank" >10.1117/12.2304955</a>
Alternative languages
Result language
angličtina
Original language name
Genetic Algorithm for Automatic tuning of neural network hyperparameters
Original language description
Articial neural networks affect our everyday life. But every neural network depends on the appropriate training set and setting of internal properties with hyperparameters. Even accurate and complete training set doesnt imply high performance of neural network algorithm. Tuning of hyperparameters is crucial for correct functionality, fast learning and high accuracy of neural networks. The hyperparameter selection relies on manual ne-tuning based on multiple full training trials. There are a lot of neural network implementation available for public and commercial use, but the setting of hyperparameters is often a neglected problem. Choosing the best structure and hyperparameters is the primary challenge in designing a neural network. This article describes a genetic algorithm for automatic selection of hyperparameters and their tuning for increasing the performance of neural networks without human interaction. The optimization algorithm accelerates the discovery of conguration, which is otherwise a time-consuming task. We evaluate the results of optimizations in comparison to naive approach and compare pro and cons of different techniques.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
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
<a href="/en/project/EF16_013%2F0001797" target="_blank" >EF16_013/0001797: CESNET E-Infrastructure - Modernisation</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Autonomous Systems: Sensors, Vehicles, Security, and the Internet of Everything
ISBN
978-1-5106-1798-8
ISSN
0277-786X
e-ISSN
neuvedeno
Number of pages
7
Pages from-to
—
Publisher name
SPIE
Place of publication
Neuveden
Event location
Orlando, Florida, United States
Event date
Apr 16, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000453556800017