Dynamic validation and relevance maintenance of neural correlates under continual learning

Скорочена інформація про документ
dc.contributor.authorVerbytskyi O. S.
dc.contributor.authorGaidaienko O. V.
dc.date.accessioned2026-06-09T10:17:33Z
dc.date.issued2025-09-25
dc.descriptionVerbytskyi, O. S. Dynamic validation and relevance maintenance of neural correlates under continual learning / O. S. Verbytskyi, O. V. Gaidaienko // Матеріали ХVІ міжнар. науково-технічна конф. "Інновації в суднобудуванні та океанотехніці". – Миколаїв : НУК. – 2025. – С. 628–631.
dc.description.abstract1Deep neural networks trained in static environments suffer from model degradation when faced with evolving data distributions (concept drift). This study proposes a framework for dynamic validation and targeted maintenance of concept-specific neurons, addressing the continual learning challenge. Building on L0-optimization for neuron localization, we introduce a "Concept Adequacy Score" to detect knowledge decay. Upon detecting drift, a localized update mechanism fine-tunes only the minimal neuron set responsible for the concept, avoiding costly full-network retraining. Experiments simulating a continual learning scenario show that our approach maintains high classification accuracy over time, reducing computational costs by an order of magnitude compared to full retraining, thereby enabling efficient and adaptive AI systems.
dc.description.provenanceSubmitted by Оксана Гайдаєнко (oksana.gaidaienko@nuos.edu.ua) on 2026-06-08T08:38:53Z workflow start=Step: reviewstep - action:claimaction No. of bitstreams: 1 Вербицкий О_3.pdf: 598988 bytes, checksum: f32b2254240fc184c2c25f95f5db90da (MD5)en
dc.description.provenanceStep: reviewstep - action:reviewaction Approved for entry into archive by Бондар Ольга (olga.bondar@nuos.edu.ua) on 2026-06-09T10:13:18Z (GMT)en
dc.description.provenanceStep: editstep - action:editaction Approved for entry into archive by Бондар Ольга (olga.bondar@nuos.edu.ua) on 2026-06-09T10:16:59Z (GMT)en
dc.description.provenanceStep: finaleditstep - action:finaleditaction Approved for entry into archive by Бондар Ольга (olga.bondar@nuos.edu.ua) on 2026-06-09T10:17:33Z (GMT)en
dc.description.provenanceMade available in DSpace on 2026-06-09T10:17:33Z (GMT). No. of bitstreams: 1 Verbytskyi.pdf: 598988 bytes, checksum: f32b2254240fc184c2c25f95f5db90da (MD5) Previous issue date: 2025-09-25en
dc.identifier.isbn978-966-321-487-0
dc.identifier.urihttps://eir.nuos.edu.ua/handle/123456789/13023
dc.language.isoen
dc.relation.ispartofseriesУДК ; 004.032.26:004.89
dc.subjectcontinual learning
dc.subjectconcept drift
dc.subjectexplainable AI
dc.subjectmodel degradation
dc.subjectlocalized finetuning
dc.subjectneural correlates.
dc.titleDynamic validation and relevance maintenance of neural correlates under continual learning
dc.typeTheses

Файли

Контейнер файлів

Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Verbytskyi.pdf
Розмір:
584.95 KB
Формат:
Adobe Portable Document Format
Завантажити

Ліцензійна угода

Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
license.txt
Розмір:
4.38 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Матеріали конференцій (ІУСтаТ)