Investigating Neural Networks with Memory Capacity to Classify Images Using Small Number of Samples

dc.contributor.advisorNguyen, Hien Van
dc.contributor.committeeMemberHan, Zhu
dc.contributor.committeeMemberBenhaddou, Driss
dc.creatorRaavi, Siri
dc.date.accessioned2018-11-30T18:12:12Z
dc.date.available2018-11-30T18:12:12Z
dc.date.createdMay 2018
dc.date.issued2018-05
dc.date.submittedMay 2018
dc.date.updated2018-11-30T18:12:12Z
dc.description.abstractDespite recent breakthroughs in the applications of deep neural networks, “One-Shot Learning” remains a persistent challenge. Traditional neural networks require huge data to learn, often through extensive iterative training. The models must re-learn their parameters to adequately incorporate the new information when new data is encountered without catastrophic interference. Architectures with augmented memory capacities offer the ability to quickly encode and retrieve new information, and hence can potentially obviate the downsides of conventional models. This thesis work is focused on demonstrating the ability of a memory-augmented neural network to rapidly assimilate new data, and leverage this data to make accurate predictions for multi-class classification after only a few samples. We compared the results of Memory Augmented Neural Network (MANN) with that of the AlexNet, and a Linear Classifier (Logistic Regression) and MANN outperformed others given a small set of samples.
dc.description.departmentElectrical and Computer Engineering, Department of
dc.format.digitalOriginborn digital
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/10657/3504
dc.language.isoeng
dc.rightsThe author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s).
dc.subjectOne-Shot Learning
dc.subjectMemory Augmented Neural Network (MANN)
dc.subjectClassification
dc.titleInvestigating Neural Networks with Memory Capacity to Classify Images Using Small Number of Samples
dc.type.dcmiText
dc.type.genreThesis
local.embargo.lift2020-05-01
local.embargo.terms2020-05-01
thesis.degree.collegeCullen College of Engineering
thesis.degree.departmentElectrical and Computer Engineering, Department of
thesis.degree.disciplineComputer and Systems Engineering
thesis.degree.grantorUniversity of Houston
thesis.degree.levelMasters
thesis.degree.nameMaster of Science

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
RAAVI-THESIS-2018.pdf
Size:
1.77 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.43 KB
Format:
Plain Text
Description:
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.81 KB
Format:
Plain Text
Description: