Thesis Details

Neural Network Training Progress Visualization

Bachelor's Thesis Student: Němcová Silvie Academic Year: 2020/2021 Supervisor: Beneš Karel, Ing.
Czech title
Vizualizace průběhu trénování neuronové sítě
Language
English
Abstract

This work studies a neural network model during its training. The aim of this thesis is to visualize the training of the model and to examine the training. To achieve this goal I choose to implement a set of tools in Python language. The implementation successfully reproduces the linear path experiment, the identification of robust and ambient layers and the visualization of the loss surface. In addition the quadratic path experiment is presented in this thesis as novel method for analyzing the neural network training progress visualization.

Keywords

Artificial intelligence, neural networks, neural network training, Python, neural network training visualization.

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade A
Date
15 June 2021
Reviewer
Baskar Murali K.
Committee
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), předseda
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Kekely Lukáš, Ing., Ph.D. (DCSY FIT BUT), člen
Rogalewicz Adam, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Veselý Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
Citation
NĚMCOVÁ, Silvie. Neural Network Training Progress Visualization. Brno, 2021. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2021-06-15. Supervised by Beneš Karel. Available from: https://www.fit.vut.cz/study/thesis/23446/
BibTeX 
@bachelorsthesis{FITBT23446,
    author = "Silvie N\v{e}mcov\'{a}",
    type = "Bachelor's thesis",
    title = "Neural Network Training Progress Visualization",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2021,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/23446/"
}

Theses

Back to top