NeuroView: Explainable Deep Network Decision Making

Simple item page
dc.contributor.advisorBaraniuk, Richard G
dc.contributor.committeeMemberBalakrishnan, Guha
dc.creatorBarberan, CJ
dc.date.accessioned2022-09-26T19:28:41Z
dc.date.available2022-09-26T19:28:41Z
dc.date.created2022-05
dc.date.issued2022-07-06
dc.date.submittedMay 2022
dc.date.updated2022-09-26T19:28:41Z
dc.description.abstractDeep neural networks (DNs) provide superhuman performance in numerous computer vision tasks, yet it remains unclear exactly which of a DN's units contribute to a particular decision. A deep network’s prediction cannot be explained in a formal mathematical manner such that you know how all the parameters contribute to the decision. NeuroView is a new family of DN architectures that are explainable by design. Each member of the family is derived from a standard DN architecture by concatenating all of the activations and feeding them into a global linear classifier. The resulting architecture establishes a direct, causal link between the state of each unit and the classification decision. We validate NeuroView on multiple datasets and classification tasks to show that it has on par performance to a typical DN. Also, we inspect how it’s unit/class mapping aids in understanding the decision-making process. In this thesis, we propose using NeuroView in other architectures such as convolutional and recurrent neural networks to show how it can aid in providing additional understanding in applications that need more explanation.
dc.format.mimetypeapplication/pdf
dc.identifier.citationBarberan, CJ. "NeuroView: Explainable Deep Network Decision Making." (2022) Diss., Rice University. <a href="https://hdl.handle.net/1911/113400">https://hdl.handle.net/1911/113400</a>.
dc.identifier.urihttps://hdl.handle.net/1911/113400
dc.language.isoeng
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.
dc.subjectdeep learning
dc.subjectexplainability
dc.subjectinterpretability
dc.subjectcomputer vision
dc.titleNeuroView: Explainable Deep Network Decision Making
dc.typeThesis
dc.type.materialText
thesis.degree.departmentElectrical and Computer Engineering
thesis.degree.disciplineEngineering
thesis.degree.grantorRice University
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BARBERAN-DOCUMENT-2022.pdf
Size:
18.19 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.6 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Electronic Theses and Dissertations