| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Učenje redkih nevronskih mrež z iterativnim rezanjem parametrov
Authors:ID Podvratnik, Nejc (Author)
ID Strnad, Damjan (Mentor) More about this mentor... New window
ID Horvat, Štefan (Comentor)
Files:.pdf MAG_Podvratnik_Nejc_2025.pdf (2,88 MB)
MD5: 95912F2F4AD466C3AC0EE9DF8A2A6F54
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Moderno globoko učenje pogosto vključuje nevronske mreže, ki imajo nepotrebno veliko število parametrov oziroma povezav. Posledica tega je višja časovna in prostorska zahtevnost pri delu z mrežami. Možna rešitev problema je hipoteza loterijskih srečk, ki pravi, da v množici povezav vsake naprej povezane nevronske mreže obstaja podmnožica, ki je manjša in ohranja enako in v nekaterih primerih tudi večjo uspešnost. Imenujemo jo zmagovita srečka. V magistrskem delu je predstavljena in dokazana hipoteza loterijske srečke ter implementiran lasten algoritem za iterativno rezanje parametrov, ki je bil testiran in analiziran na različnih arhitekturah, podatkovnih zbirkah in hiperparametrih.
Keywords:strojno učenje, redka nevronska mreža, hipoteza loterijskih srečk, rezanje
Place of publishing:Maribor
Publisher:[N. Podvratnik]
Year of publishing:2025
PID:20.500.12556/DKUM-91709 New window
UDC:004.85:004.032.26(043.2)
COBISS.SI-ID:229524227 New window
Publication date in DKUM:04.03.2025
Views:157
Downloads:62
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and 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:29.01.2025

Secondary language

Language:English
Title:Sparse neural network learning with iterative parameter removal
Abstract:Modern deep learning often involves neural networks that have an unnecessarily large number of parameters or connections. This results in a higher time and space complexity when working with networks. A possible solution to the problem is the lottery ticket hypothesis, which states that in a set of connections of any feedforward neural network there is a subset that is smaller and maintains the same and, in some cases, even higher effectiveness. We call them winning tickets. In the content of this work, we will present and prove the lottery ticket hypothesis, implement our own algorithm for iterative pruning of parameters and test and analyze it on various architectures, datasets and hyperparameters.
Keywords:machine learning, sparse neural network, lottery ticket hypothesis, pruning


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica