| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Pristop za izboljšanje pravičnosti v strojnem učenju z uporabo arhitekture učitelj-študent in učenjem z učnim načrtom : magistrsko delo
Authors:ID Trdin, Peter (Author)
ID Karakatič, Sašo (Mentor) More about this mentor... New window
ID Colakovic, Ivona (Comentor)
Files:.pdf MAG_Trdin_Peter_2025.pdf (2,47 MB)
MD5: 0D991BBEB856640E02445C73CADB2A66
 
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 raziskujemo, kako lahko arhitektura učitelj-študent v kombinaciji z učenjem po učnem načrtu pripomore k zmanjševanju nepravičnosti v modelih strojnega učenja. Razvili smo več pristopov za prenos znanja, pri čemer smo uporabili obteževanje po senzitivnih skupinah in strukturirano inkrementalno učenje. Rezultati eksperimentov na zbirki Adult Income kažejo, da ti pristopi pomembno izboljšajo pravičnost napovedi, čeprav pogosto z rahlim zmanjšanjem točnosti. Magistrsko delo prispeva k razumevanju vpliva strukturiranega učenja in prenosa znanja na pravičnost napovednih modelov.
Keywords:strojno učenje, pravičnost, arhitektura učitelj-študent, učenje z učnim načrtom, destilacija znanja
Place of publishing:Maribor
Place of performance:Maribor
Publisher:P. Trdin
Year of publishing:2025
Number of pages:1 spletni vir (1 datoteka PDF (XIII, 62 str.))
PID:20.500.12556/DKUM-95853 New window
UDC:004.85(043.2)
COBISS.SI-ID:266788099 New window
Publication date in DKUM:22.12.2025
Views:165
Downloads:33
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:02.11.2025

Secondary language

Language:English
Title:Approach for improving fairness in machine learning using teacher-student architecture and curriculum learning
Abstract:This master's thesis explores how the teacher-student architecture, combined with curriculum learning, can help reduce unfairness in machine learning models. We developed several knowledge transfer approaches that incorporate weighting by sensitive groups and structured incremental learning. Experimental results on the Adult Income dataset show that these approaches significantly improve prediction fairness, although often at a slight cost to accuracy. The thesis contributes to understanding the impact of structured learning and knowledge transfer on the fairness of predictive models.
Keywords:machine learning, fairness, teacher-student architecture, curriculum learning, knowledge distillation


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