Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/30167
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Giuliano A | - |
dc.contributor.author | Hilal W | - |
dc.contributor.author | Alsadi N | - |
dc.contributor.author | Yawney J | - |
dc.contributor.author | Gadsden SA | - |
dc.contributor.editor | Petruccelli JC | - |
dc.contributor.editor | Preza C | - |
dc.date.accessioned | 2024-09-08T17:49:48Z | - |
dc.date.available | 2024-09-08T17:49:48Z | - |
dc.date.issued | 2023-07-19 | - |
dc.identifier.issn | 0277-786X | - |
dc.identifier.issn | 1996-756X | - |
dc.identifier.uri | http://hdl.handle.net/11375/30167 | - |
dc.description.abstract | Convolutional neural networks (CNNs) are a widely researched neural network architecture that has demonstrated exemplary performance in image processing tasks and applications compared to other popular deep learning and machine learning methods resulting in state-of-the-art performance in many image processing tasks such as image classification and segmentation. CNNs operate on the principle of automated learning of filters or kernels in contrast with hand-crafted digital filters to extrapolate features from images effectively. This paper aims to investigate whether a matrix's determinant can be used to preserve information in CNN convolutional layers. Geometrically the absolute value of the determinant is defined as a scaling factor of the linear transformation resulting from matrix multiplication. When an image's size is reduced into a feature space through a convolutional layer of a CNN, some information is lost. The intuition is that the scaling factor that results from the determinant of the pooling layer matrix can enhance the feature space introducing scaling as a piece of information in the feature space as well as lost relations between adjacent pixels. | - |
dc.publisher | SPIE, the international society for optics and photonics | - |
dc.rights.uri | 7 | - |
dc.subject | 40 Engineering | - |
dc.subject | 4006 Communications Engineering | - |
dc.subject | 4009 Electronics, Sensors and Digital Hardware | - |
dc.subject | 51 Physical Sciences | - |
dc.subject | 5102 Atomic, Molecular and Optical Physics | - |
dc.subject | Machine Learning and Artificial Intelligence | - |
dc.subject | Networking and Information Technology R&D (NITRD) | - |
dc.title | Normalized determinant pooling layer in CNNs for multi-label classification | - |
dc.type | Article | - |
dc.date.updated | 2024-09-08T17:49:47Z | - |
dc.contributor.department | Mechanical Engineering | - |
dc.rights.license | Attribution-NonCommercial-NoDerivs - CC BY-NC-ND | - |
dc.identifier.doi | https://doi.org/10.1117/12.2663916 | - |
Appears in Collections: | Mechanical Engineering Publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
160-1252309.pdf | Published version | 728.11 kB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.