lukas/bachelor-thesis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

modify title and rm disclaimer
All checks were successful
Build Typst document / build_typst_documents (push) Successful in 18s
Details

Browse Source
This commit is contained in:
lukas-heiligenbrunner
2025-02-04 18:56:46 +01:00
parent cf6f4f96ac
commit 7681b4afce
28 changed files with 1207 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
main.typ
View File

@ -1,4 +1,4 @@
#import "@preview/not-jku-thesis:0.1.0": jku-thesis
#import "lib/jkutemplate/template.typ": jku-thesis
#import "utils.typ": inwriting, draft, todo, flex-caption, flex-caption-styles
#import "glossary.typ": glossary
@ -39,7 +39,6 @@
#let date = datetime.today() // not today: datetime(year: 1969, month: 9, day: 6,)
#let k-number = "k12104785"
#show: jku-thesis.with(
thesis-type: "Bachelor",
degree: "Bachelor of Science",
@ -50,7 +49,7 @@
author: "Lukas Heiligenbrunner",
date: date,
place-of-submission: "Linz",
title: "Few shot learning for anomaly detection",
title: "Few-Shot Learning for Anomaly Detection",
abstract-en: [//max. 250 words
This thesis explores the application of Few-Shot Learning (FSL) in anomaly detection, a critical area in industrial and automotive domains requiring robust and efficient algorithms for identifying defects.
Traditional methods, such as PatchCore and EfficientAD, achieve high accuracy but often demand extensive training data and are sensitive to environmental changes, necessitating frequent retraining.