Few-Shot Learning Networks: Optimization Techniques and Trends

dc.contributor.committeeChairSheng, Victor S.
dc.contributor.committeeMemberSalman, Tara
dc.creatorVidaurri, Jeremy
dc.creator.orcid0009-0002-2211-6672
dc.date.accessioned2024-04-01T15:10:36Z
dc.date.available2024-04-01T15:10:36Z
dc.date.issued2023-05
dc.description.abstractMost modern machine learning systems require to be trained over a large set of data. This is useful when there is readily large amounts of data. In recent years, few-shot learning has been proposed to circumvent this issue. Instead, the machine is given limited amounts of data and can make accurate predictions. Although the initial data may be limited, data can be artificially developed through data augmentation. Unfortunately, few-shot learning systems are not at the state where they can be utilized reliably. There is possibilities for these systems to be optimized through implementing dropout and hyperparameter tuning. This study is designed to analyze any trends and techniques that may allow for higher performance generally.
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/2346/97793
dc.language.isoen
dc.rights.availabilityUnrestricted.
dc.subjectmachine learning
dc.subjectoptimization
dc.subjectlearning paradigms
dc.subjectsupervised learning
dc.subjecthyperarameter tuning
dc.titleFew-Shot Learning Networks: Optimization Techniques and Trends
dc.typeThesis
thesis.degree.collegeEdward E. Whitacre Jr. College of Engineering
thesis.degree.collegeHonors College
thesis.degree.departmentComputer Science
thesis.degree.disciplineComputer Science
thesis.degree.grantorTexas Tech University
thesis.degree.levelBachelor's
thesis.degree.nameBachelor of Science

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
VIDAURRI-HONORS-2023.pdf
Size:
352.84 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.57 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections