Bc. Miriam Galanová
Bachelor's thesis
Vizualizace hlubokého učení časových řad
Visualization of Deep Learning Time Series
Abstract:
The thesis describes three neural network visualization tools implemented for an industrial partner KGT Investments Ltd. The tools were developed in collaboration with the aforementioned partner. The first tool allows visualisation of the process of network learning, the second tool displays the selected network through the weights between the layers, and the third tool displays the preferred patterns …moreAbstract:
Táto práca opisuje tri nástroje na vizualizáciu neurónových sietí implementované pre priemyselného partnera, ktorým je firma KGT Investments Ltd. Nástroje boli vyvíjané v spolupráci so spomínaným partnerom. Prvý nástroj umožňuje vizualizáciu priebehu učenia siete, druhý zobrazuje vybranú sieť prostredníctvom váh medzi vrstvami a tretí zobrazuje preferované vzory siete pre jednotlivé klasifikačné kategórie …more
Language used: Slovak
Date on which the thesis was submitted / produced: 28. 5. 2018
Identifier:
https://is.muni.cz/th/de9qq/
Thesis defence
- Date of defence: 29. 6. 2018
- Supervisor: doc. RNDr. Tomáš Brázdil, Ph.D.
- Reader: RNDr. Karel Vaculík
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsBachelor programme / field:
Informatics / Artificial Intelligence and Natural Language Processing
Theses on a related topic
-
Multilayer feedforward neural networks based on multi-valued neurons
Miroslav Hlaváček -
Multivariate Anomaly Detection System with System-Dynamics-Reflective Neural Architectures
Filip HRUBÝ -
The analysis of drought indices forecast using neural networks
Anna Morozova -
The Application of Neural Networks in Stock-Exchange Investing
Radoslaw Ogrodnik -
Simulating drone automation in agriculture using neural networks
Jakub Valent -
Particle detection in electron microscopy images using neural networks
Roman Ďuriš -
Simulation of Multiple Motile Agents Using Neural Networks
Branislav Ševc -
Application of Graph Neural Networks in a Selected Domain
Emanuel Dopater