YorkSpace has migrated to a new version of its software. Access our Help Resources to learn how to use the refreshed site. Contact diginit@yorku.ca if you have any questions about the migration.
 

Predicting Retinal Ganglion Cell Responses Based on Visual Features via Graph Filters

Simple item page
dc.contributor.advisorEckford, Andrew W.
dc.contributor.authorParhizkar, Yasaman
dc.date.accessioned2023-12-08T14:41:27Z
dc.date.available2023-12-08T14:41:27Z
dc.date.issued2023-12-08
dc.date.updated2023-12-08T14:41:26Z
dc.degree.disciplineElectrical and Computer Engineering
dc.degree.levelMaster's
dc.degree.nameMASc - Master of Applied Science
dc.description.abstractThis thesis presents a novel graph-based approach to classify video clips with binary labels. Each video clip is described by a feature vector instead of raw pixel values. At the model's core, a similarity graph is defined where each node is associated with a feature vector and its corresponding label. The weight of an edge connecting two nodes delineates the similarity of the nodes' feature vectors which is computed via the Mahalanobis distance and its metric matrix. The metric matrix is learned using labeled training data. Unknown labels are then estimated using the optimized metric and the similarity graph. The main advantage of our model is enabling interpretations of how the predictions are made. Nevertheless, the model achieves competitive accuracy with state-of-the-art approaches as well. We apply this model to a retinal coding problem where explainability is essential to gain conceptual insight about the retina.
dc.identifier.urihttps://hdl.handle.net/10315/41731
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectArtificial intelligence
dc.subjectApplied mathematics
dc.subjectBioinformatics
dc.subject.keywordsGraph signal processing
dc.subject.keywordsGraph learning
dc.subject.keywordsGraph filter
dc.subject.keywordsMetric learning
dc.subject.keywordsMahalanobis distance
dc.subject.keywordsVideo classification
dc.subject.keywordsInterpretability
dc.subject.keywordsExplainability
dc.subject.keywordsExplainable AI
dc.subject.keywordsRetinal ganglion cells
dc.subject.keywordsBiomedical signal processing
dc.subject.keywordsRetinal code
dc.subject.keywordsLarge margin nearest neighbor
dc.subject.keywordsGraph Laplacian regularizer
dc.subject.keywordsGershgorin disc
dc.subject.keywordsGershgorin disc perfect alignment
dc.subject.keywordsSimilarity graph
dc.subject.keywordsSemi-supervised learning
dc.subject.keywordsFeature extraction
dc.subject.keywordsScale-invariant feature transform
dc.subject.keywordsSIFT
dc.subject.keywords3D scale-invariant feature transform
dc.subject.keywordsTransfer learning
dc.subject.keywordsPre-trained convolutional neural network
dc.titlePredicting Retinal Ganglion Cell Responses Based on Visual Features via Graph Filters
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Parhizkar_Yasaman_2023_Masters.pdf
Size:
8.43 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Electrical and Computer Engineering

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.