Метаевристичнi алгоритми для обрiзки нейронних мереж

dc.contributor.advisorШвай, Надіяuk_UA
dc.contributor.authorКотляренко, Анастасiяuk_UA
dc.date.accessioned2025-09-03T12:44:09Z
dc.date.available2025-09-03T12:44:09Z
dc.date.issued2025
dc.description.abstractThis work studies neural network pruning with metaheuristic optimization methods. Pruning was formulated as an optimization problem with a target function that is a weighted sum of neural network accuracy and sparsity. This problem was solved with stochastic metaheuristic methods (Genetic Algorithm and Particle Swarm Optimization) that generate binary masks. Obtained results demonstrate that pruning with metaheuristic methods is comparative with 𝐿2 pruning when finetuning is possible and is significantly more performant when no post-pruning finetuning is available.en_US
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/36404
dc.language.isoen_USen_US
dc.statusfirst publisheden_US
dc.subjectneural networksen_US
dc.subjectpruningen_US
dc.subjectmetaheuristicen_US
dc.subjectGenetic Algorithmen_US
dc.subjectParticle Swarm Optimizationen_US
dc.subject𝐿2 pruningen_US
dc.subjectbachelor`s thesisen_US
dc.titleМетаевристичнi алгоритми для обрiзки нейронних мережuk_UA
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Kotliarenko_Bakalavrska_robota.pdf
Size:
336.47 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
Kotliarenko_Bakalavrska_robota_1.pdf
Size:
1.19 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: