Thesis Details

Interpretace konvolučních neuronových sítí

Bachelor's Thesis Student: Kamenický Daniel Academic Year: 2020/2021 Supervisor: Hradiš Michal, Ing., Ph.D.
English title
Explainable Convolutional Neural Networks
Language
Czech
Abstract

The aim of this work was to compare several methods for visualizing the features of each class on the input pixel layer of the CNN. Each method uses a different algorithm, based on gradients, to compute the resulting values. Using the implementation of each method, the resultant values of the methods are obtained by using the equation of energy concentration. The resultant values are presented in tables and graphs from which the success rate of the result of the work can be read. The difference between the methods and comparison of their results can be read from the work. This makes it possible to get an overview of gradient based visualization methods.

Keywords

CNN, NN, MLP, gradient, preceptron, sigmoid, bias, threshold, weights, hook

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade E
Date
14 June 2021
Reviewer
Herout Adam, prof. Ing., Ph.D.
Committee
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT), předseda
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Citation
KAMENICKÝ, Daniel. Interpretace konvolučních neuronových sítí. Brno, 2021. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2021-06-14. Supervised by Hradiš Michal. Available from: https://www.fit.vut.cz/study/thesis/23910/
BibTeX 
@bachelorsthesis{FITBT23910,
    author = "Daniel Kamenick\'{y}",
    type = "Bachelor's thesis",
    title = "Interpretace konvolu\v{c}n\'{i}ch neuronov\'{y}ch s\'{i}t\'{i}",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2021,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/23910/"
}

Theses

Back to top