BCAP: An Artificial Neural Network Pruning Technique to Reduce Overfitting

dc.contributor.advisorOates, Tim
dc.contributor.authorBrantley, Kiante Damont
dc.contributor.departmentComputer Science and Electrical Engineering
dc.contributor.programComputer Science
dc.date.accessioned2019-10-11T13:39:16Z
dc.date.available2019-10-11T13:39:16Z
dc.date.issued2016-01-01
dc.descriptionIncludes 1 pdf supplement with slides.
dc.description.abstractDetermining the optimal size of a neural network is complicated. Neural networks, with many free parameters, can be used to solve very complex problems. However, these neural networks are susceptible to overfitting. BCAP (Brantley-Clark Artificial Neural Network Pruning Technique) addresses overfitting by combining duplicate neurons in a neural network hidden layer, thereby forcing the network to learn more distinct features. We compare hidden units using the cosine similarity, and combine those that are similar with each other within a threshold. By doing so the co-adaption of the neurons in the network is reduced because hidden units that are highly correlated (i.e. similar) are combined. In this paper we show evidence that BCAP is successful in reducing network size while maintaining accuracy, or improving accuracy of neural networks during and after training.
dc.genretheses
dc.identifierdoi:10.13016/m2jwjm-bxqk
dc.identifier.other11466
dc.identifier.urihttp://hdl.handle.net/11603/15471
dc.languageen
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Theses and Dissertations Collection
dc.relation.ispartofUMBC Graduate School Collection
dc.relation.ispartofUMBC Student Collection
dc.rightsThis item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
dc.sourceOriginal File Name: Brantley_umbc_0434M_11466.pdf
dc.subjectDeep Learning
dc.subjectNeural Network Optimization
dc.subjectNeural Networks
dc.subjectPruning Neural Networks
dc.titleBCAP: An Artificial Neural Network Pruning Technique to Reduce Overfitting
dc.typeText
dcterms.accessRightsDistribution Rights granted to UMBC by the author.

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Brantley_umbc_0434M_11466.pdf
Size:
873.12 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
BrantleySupplementSlides.pdf
Size:
4.75 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Boukouvalas_Open.pdf
Size:
48.66 KB
Format:
Adobe Portable Document Format
Description: