Self-improving generative artificial neural network for pseudorehearsal incremental class learning

Vista sencilla de ítem
dc.contributor.authorMellado, Diego
dc.contributor.authorSaavedra, Carolina
dc.contributor.authorChabert, Sterena
dc.contributor.authorTorres, Romina
dc.contributor.authorSalas, Rodrigo
dc.date.accessioned2023-03-29T13:03:44Z
dc.date.available2023-03-29T13:03:44Z
dc.date.issued2019
dc.descriptionIndexación Scopuses
dc.description.abstractDeep learning models are part of the family of artificial neural networks and, as such, they suffer catastrophic interference when learning sequentially. In addition, the greater number of these models have a rigid architecture which prevents the incremental learning of new classes. To overcome these drawbacks, we propose the Self-Improving Generative Artificial Neural Network (SIGANN), an end-to-end deep neural network system which can ease the catastrophic forgetting problem when learning new classes. In this method, we introduce a novel detection model that automatically detects samples of new classes, and an adversarial autoencoder is used to produce samples of previous classes. This system consists of three main modules: a classifier module implemented using a Deep Convolutional Neural Network, a generator module based on an adversarial autoencoder, and a novelty-detection module implemented using an OpenMax activation function. Using the EMNIST data set, the model was trained incrementally, starting with a small set of classes. The results of the simulation show that SIGANN can retain previous knowledge while incorporating gradual forgetfulness of each learning sequence at a rate of about 7% per training step. Moreover, SIGANN can detect new classes that are hidden in the data with a median accuracy of 43% and, therefore, proceed with incremental class learning.es
dc.identifier.citationAlgorithms Volume 12, Issue 10 2019 Article number 206es
dc.identifier.doi10.3390/a12100206en
dc.identifier.issn1999-4893
dc.identifier.urihttps://repositorio.unab.cl/xmlui/handle/ria/48012
dc.language.isoenes
dc.publisherAlgorithmses
dc.rights.licenseAttribution 4.0 International (CC BY 4.0)en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectArtificial neural networkses
dc.subjectCatastrophic interferencees
dc.subjectDeep learninges
dc.subjectGenerative neural networkses
dc.subjectIncremental learninges
dc.subjectNovelty detectiones
dc.titleSelf-improving generative artificial neural network for pseudorehearsal incremental class learninges
dc.typeArtículoes
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Selfimproving-generative-artificial-neural-network-for-pseudorehearsal-incremental-class-learningAlgorithms.pdf
Tamaño:
1.12 MB
Formato:
Adobe Portable Document Format
Descripción:
TEXTO COMPLETO EN INGLÉS
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
FIng - Artículos de Revista