Explainability of Deep Learning for Genomic sequences – Bc. Jakub Poláček
Bc. Jakub Poláček
Master's thesis
Explainability of Deep Learning for Genomic sequences
Explainability of Deep Learning for Genomic sequences
Abstract:
Hoci algoritmy strojového učenia vykazujú neprekonateľný prísľub v klasifikácii a detekovaní vlastností genomických dát, mnohé z uvedených algoritmov stále predstavujú výzvu v ohľade vysvetlovania ich rozhodovacích procesov. To často spôsobuje nízku dôveru k presnosti ich výsledkov. Najväčším kameňom úrazu z techník strojového učenia sú v tomto nepochybne neurónové siete. Keďže sa ukazuje, že neurónové …moreAbstract:
While machine learning algorithms show unparalleled promise in genomic data classification and feature detection, many of said algorithms still pose a challenge in proper explanation of their decision processes. This often causes low confidence towards the veracity of their results. The biggest offenders among the class of machine learning techniques are indisputably neural networks. Since neural networks …more
Language used: English
Date on which the thesis was submitted / produced: 14. 12. 2021
Identifier:
https://is.muni.cz/th/lzelx/
Thesis defence
- Date of defence: 4. 2. 2022
- Supervisor: PhD Panagiotis Alexiou
- Reader: Mgr. Vojtěch Bystrý, Ph.D.
Citation record
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 InformaticsMaster programme / field:
Artificial intelligence and data processing / Machine learning and artificial intelligence
Theses on a related topic
-
Interpretability of Neural Networks in Drug Design
Abd Alkareem ALJEIROUDI -
Exchange rates predictions using machine learning methods
Yaroslav Korobka