Bc. Adrián Bindas

Bachelor's thesis

Comparison of methods for clustering convolutional neural network intercomputation values with respect to explainability

Comparison of methods for clustering convolutional neural network intercomputation values with respect to explainability
Abstract:
Konvolučné neurónové siete našli svoje uplatnenie v histopatológii, kde pomáhajú odborníkom pri identifikácii zhubného tkaniva. Využitie neurónových sietí je ale v medicíne limitované ich vysvetliteľnosťou. Táto práca sa zaoberá aplikáciou zhlukovania ako metódy vysvetliteľnosti pre konvolučnú neurónovú sieť natrénovanú na dátach z Masarykovho onkologického ústavu. Zhlukovanie aktivačných hodnôt vygenerovaných …more
Abstract:
Convolutional neural networks have found their use in histopathology, assisting experts in the identification of malignant tissue. The use of artificial neural networks in medicine is, however, limited by their explainability. The thesis is concerned with the application of clustering as an explainability method for CNN trained on histopathological data from Masaryk Memorial Cancer Institute. The clustering …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 23. 5. 2024

Thesis defence

  • Date of defence: 26. 6. 2024
  • Supervisor: Mgr. Adam Bajger
  • Reader: doc. RNDr. Martin Maška, 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 informatiky

Masaryk University

Faculty of Informatics

Bachelor programme / field:
Informatics / Informatics