Thesis Details

Zjednodušené násobení v konvolučních neuronových sítích

Master's Thesis Student: Juhaňák Pavel Academic Year: 2018/2019 Supervisor: Sekanina Lukáš, prof. Ing., Ph.D.
English title
Simplified Multiplication in Convolutional Neural Networks
Language
Czech
Abstract

This thesis provides an introduction to classical and convolutional neural networks. It describes how hardware multiplication is conventionally performed and optimized. A simplified multiplication method is proposed, namely multiplierless multiplication. This method is implemented and integrated into the TypeCNN library. The cost of the hardware solution of both conventional and simplified multipliers is estimated. The thesis also introduces software tools developed to work with convolutional neural networks and datasets used to test them in the image classification task. Test architectures and experimentation methodology are proposed. The results are evaluated, and both the classification accuracy and cost of the hardware solution are discussed.

Keywords

artificial intelligence, soft computing, neuron, neural networks, convolutional neural networks, multiplication, optimization, simplified multiplication, multiplierless multiplication

Department
Degree Programme
Information Technology, Field of Study Information Technology Security
Files
Status
defended, grade C
Date
14 June 2019
Reviewer
Committee
Hruška Tomáš, prof. Ing., CSc. (DIFS FIT BUT), předseda
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
Hrdina Jaroslav, doc. Mgr., Ph.D. (DADM FME BUT), člen
Malinka Kamil, Mgr., Ph.D. (DITS FIT BUT), člen
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Citation
JUHAŇÁK, Pavel. Zjednodušené násobení v konvolučních neuronových sítích. Brno, 2019. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2019-06-14. Supervised by Sekanina Lukáš. Available from: https://www.fit.vut.cz/study/thesis/21476/
BibTeX
@mastersthesis{FITMT21476,
    author = "Pavel Juha\v{n}\'{a}k",
    type = "Master's thesis",
    title = "Zjednodu\v{s}en\'{e} n\'{a}soben\'{i} v konvolu\v{c}n\'{i}ch neuronov\'{y}ch s\'{i}t\'{i}ch",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2019,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/21476/"
}
Back to top