Faster Convolutional Neural Networks

Simple item page
dc.contributor.advisorHendriks, L.
dc.contributor.advisorGerven, M.A.J. van
dc.contributor.authorÇalli, E.
dc.contributor.otherReSnapen_US
dc.date.issued2017-08-29
dc.description.abstractThere exists a gap between the computational cost of state of the art image processing models and the processing power of publicly available devices. This gap is reducing the applicability of these promising models. Trying to bridge this gap, first we investigate pruning and factorization to reduce the computational cost of a model. Secondly, we look for alternative convolution operations to design state of the art models. Thirdly, using these alternative convolution operations, we train a model for the CIFAR-10 classifi cation task. Our proposed model achieves comparable results (91:1% top-1 accuracy) to ResNet-20 (91:25% top-1 accuracy) with half the model size and one-third floating point operations. Finally, we apply pruning and factorization and observe that these methods are ineffective in reducing the computational complexity and preserving the accuracy of our proposed model.en_US
dc.identifier.urihttp://theses.ubn.ru.nl/handle/123456789/5233
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationMaster Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeMasteren_US
dc.titleFaster Convolutional Neural Networksen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Calli, E._MSc_Thesis_2017.pdf
Size:
928.77 KB
Format:
Adobe Portable Document Format
Description:
Thesis text
Download
Collections
Faculteit der Sociale Wetenschappen