A comparative analysis of Gabor filters and biologically inspired learning rules for image classification implementing Spiking Neural Networks

Vista sencilla de ítem
dc.contributor.authorGarcía Campos, Carlos Alan
dc.contributor.codirectorOkuno, Hirotsugu
dc.contributor.directorMorales Carbajal, Ricardo
dc.coverage.placeofpublicationMexicali, Baja California.
dc.date.accessioned2025-03-18T02:23:53Z
dc.date.available2025-03-18T02:23:53Z
dc.date.created2025
dc.degree.deparmentUniversidad Autónoma de Baja California, Instituto de Ingeniería, Mexicali.
dc.degree.grantorTesis de Maestría / master Thesis.
dc.degree.nameMaestría y Doctorado en Ciencias e Ingeniería.
dc.description.abstractPlastic changes on the synapse drive by spike-timing have been of great interestas the main learning rule for spiking neural networks. Spike-timing-based rules arebuilt to model the behavior of a region on the brain related to experimental data inneuroscience, therefore can lead to differences in the moment of implementing therule within a spiking network. This work compares the performance of a pair-wiseand a triplet STDP with different spike interactions to clear an MNIST classificationtask. A bio-inspired preprocessing stage was implemented that consisted of a Gaborfilter (as a model of the simple cells mechanism orientation selectivity) and an inputnormalization for a homogeneous brightness level of each image. The highlightsof this work are 1) The consistent improvement of the model accuracy wheneverthey added the Gabor filter to the inputs; 2) The input normalization to preventthe overfitting of the model; 3) The Gabor filter helps to correct decoding of someimages of the dataset on the evaluation test.
dc.format.extent69 p. ; il. col.
dc.format.mimetypepdf
dc.identifier.urihttps://hdl.handle.net/20.500.12930/12114
dc.language.isospa
dc.publisherUniversidad Autónoma de Baja California.
dc.relation.urlhttps://drive.google.com/file/d/1jUWURFzAfflbH7JzGXP1qUD80Qc8-kcS/view?usp=sharing
dc.rightsopenAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4
dc.subjectRedes neuronales (Informática) ||Tesis y disertaciones académicas||Redes neurales (computadores) ||Tesis y disertaciones académicas||lemb||Redes neuronales (Informática) Software ||Tesis y disertaciones académicas.
dc.subject.lccQA76.87 G37 2025
dc.titleA comparative analysis of Gabor filters and biologically inspired learning rules for image classification implementing Spiking Neural Networks
dc.uabc.bibliographycNoteIncluye referencias bibliográficas.
dc.uabc.bilbiotecaMEXICALI
dc.uabc.identifier272379
dc.uabc.numInventarioMXL125429
dc.uabc.typeMaterialTESIS
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
MXL125429.pdf
Tamaño:
2.73 MB
Formato:
Adobe Portable Document Format
Descripción:
Descargar
Colecciones
Tesis de Maestría (Mexicali)