Bc. Erik Benovic
Master's thesis
Neuronové sítě a jejich aplikace
Neural Networks and their Applications
Abstract:
In this thesis, we study neural networks and their application in actuarial science. We provide a description of algorithms that form a base of neural networks with applications to various problems. Mainly, we introduce an alternative model to Poisson regression rate models of a non-life insurance portfolio. We build several neural network models with an embedded Poisson regression layer and analyze …moreAbstract:
V tejto diplomovej práci sa venujeme neurónovým sieťam a ich použití v aktuárskej matematike. Poskytujeme vysvetujúci opis algoritmov, ktoré tvoria základ neurónových sietí s aplikáciami pre rôzne typy úloh. Predstavíme alternatívny model k zovšeobecneným lineárnym modelom pre modelovanie frekvencie počtu poistných udalostí pre portfólio neživotného poistenia. Zostrojíme niekoľko neurónových sieti …more
Language used: Slovak
Date on which the thesis was submitted / produced: 22. 5. 2021
Identifier:
https://is.muni.cz/th/s93mf/
Thesis defence
- Date of defence: 28. 6. 2021
- Supervisor: doc. RNDr. Martin Kolář, Ph.D.
- Reader: Mgr. Silvie Zlatošová, Ph.D.
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, Přírodovědecká fakultaMasaryk University
Faculty of ScienceMaster programme / field:
Applied Mathematics / Statistics and data analysis
Theses on a related topic
-
Implementation of Sample Selection Estimators into Double Machine Learning Framework
Michaela Kecskésová -
Fiscal multipliers through machine learning
Juraj Szitás -
Detection of Android Malware Using Machine Learning
Matúš Šikyňa -
Machine Learning for Phishing URL Detection
Juraj Smeriga -
Supervised and Unsupervised Machine Learning Methods for System Log Anomaly Detection
Júlia Ščensná -
Reinforcement Learning for Efficient Attack Agents Training
Glenn Fischer -
Detecting user actions from encrypted traffic using machine learning
Tomáš Babej -
Learning algorithms in processing of various difficult medical and environmental data
Tomáš Hudík