Dropout for Neural Networks Pruning
| dc.contributor.advisor | Швай, Надія | uk_UA |
| dc.contributor.author | Семенець, Дарина | uk_UA |
| dc.date.accessioned | 2025-09-03T13:52:29Z | |
| dc.date.available | 2025-09-03T13:52:29Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract | In this study, the hypothesis is examined whether Dropout masks can be used for structural pruning without further evaluating the importance of individual filters or weight. It was decided to compare a Dropout-based approach, which is based on the utilization of binary Dropout masks, with a classical L2-Norm-based pruning method. For this task, we manually designed an architecture of a convolutional neural network with a custom Dropout. The research undergoes the following phases: designing a mask generation mechanism, preprocessing data, training of model, implementing of pruning algorithms, and conducting experiments using the Imagenette2 dataset. Our idea is to determine whether Dropout pruning can offer a reliable alternative to traditional methods, especially under different levels of sparsity and stochasticity. | en_US |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/36412 | |
| dc.language.iso | en_US | en_US |
| dc.status | first published | en_US |
| dc.subject | Pruning | en_US |
| dc.subject | Dropout | en_US |
| dc.subject | L2 | en_US |
| dc.subject | Convolutional Neural Network | en_US |
| dc.subject | Algorithm | en_US |
| dc.subject | Training | en_US |
| dc.subject | Binary Mask | en_US |
| dc.subject | Seed | en_US |
| dc.subject | bachelor`s thesis | en_US |
| dc.title | Dropout for Neural Networks Pruning | en_US |
| dc.title.alternative | Dropout як метод обрізки нейронних мереж | uk_UA |
| dc.type | Other | en_US |
Files
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: