Vpliv kvantizacije na učinkovitost globokih nevronskih mrež : magistrsko delo

Oprešnik, Jakob

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Vpliv kvantizacije na učinkovitost globokih nevronskih mrež : magistrsko delo
Authors:	ID Oprešnik, Jakob (Author) ID Strnad, Damjan (Mentor) More about this mentor... ID Lukač, Luka (Comentor)
Files:	MAG_Opresnik_Jakob_2025.pdf (5,77 MB) MD5: CC9BB06378702EBD88F34A37D206FDC2
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	V magistrskem delu predstavimo različne tehnike kvantizacije globokih nevronskih mrež in raziskujemo njihov vpliv na učinkovitost modelov. Na klasifikacijskem modelu ResNet-18 in regresijskem LSTM primerjamo metode kvantizacije med učenjem in po učenju, pri čemer eksperimentiramo s kvantizacijo uteži, aktivacij in gradientov pri bitni širini 16 in 8. Rezultati so v skladu s pričakovanji in kažejo, da določene metode znatno zmanjšajo velikost modelov in povečajo hitrost sklepanja ob ohranjanju primerljive točnosti, kar omogoča učinkovito implementacijo modelov na napravah z omejenimi računalniškimi viri.
Keywords:	kvantizacija, kvantizacija po učenju, kvantizacija med učenjem, nevronska mreža, globoko učenje
Place of publishing:	Maribor
Place of performance:	Maribor
Publisher:	[J. Oprešnik]
Year of publishing:	2025
Number of pages:	1 spletni vir (1 datoteka PDF (XII, 47 str.))
PID:	20.500.12556/DKUM-95349
UDC:	004.032.26(043.2)
COBISS.SI-ID:	257236227
Publication date in DKUM:	17.10.2025
Views:	164
Downloads:	73
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	15.09.2025

Secondary language

Language:	English
Title:	The impact of quantization on the performance of deep neural networks
Abstract:	This master's thesis presents various quantization techniques for deep neural networks and investigates their impact on model performance. We evaluate the ResNet-18 classification model and an LSTM regression model using quantization methods applied during and after training, experimenting with the quantization of weights, activations, and gradients at bit widths of 16 and 8. The results align with expectations and show that certain methods significantly reduce model size and improve inference speed, while maintaining comparable accuracy, thereby enabling efficient deployment of models on devices with limited computational resources.
Keywords:	quantization, post-training quantization, quantization-aware training, neural network, deep learning

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back