Adaptation of Number of Filters in the Convolution Layer of a Convolutional Neural Network Using the Fuzzy Gravitational Search Algorithm Method and Type-1 Fuzzy Logic
Título del documento: Adaptation of Number of Filters in the Convolution Layer of a Convolutional Neural Network Using the Fuzzy Gravitational Search Algorithm Method and Type-1 Fuzzy Logic
Revista: Computación y sistemas
Base de datos:
Número de sistema: 000560707
ISSN: 1405-5546
Autors: 1
2
Institucions: 1Instituto Tecnológico de Tijuana, Baja California. México
2Instituto Tecnológico de Tijuana, Computer Science in the Graduate Division, Baja California. México
Any:
Període: Abr-Jun
Volum: 26
Número: 2
Paginació: 511-535
País: México
Idioma: Inglés
Resumen en inglés This paper presents a model of the search for adaptation of parameters and the creation of the membership functions of various fuzzy systems created using the fuzzy gravitational algorithm (FGSA). These fuzzy systems were created to find the optimal number of filters to enter a convolutional neural network (CNN) with an architecture of two convolution layers, as well as two pooling layers respectively and a classification layer, which is responsible for recognizing images. With this model, the results obtained by optimizing this CNN with the FGSA algorithm and the adaptation of parameters using this same algorithm are compared to form the membership functions of fuzzy systems. Both methods and their results are comparing with each other.
Keyword: CNN,
FGSA,
Number of filters,
Fuzzy logic,
Fuzzy systems,
Adaptation of parameters,
ORL database,
Feret database,
MNIST database
Text complet: Texto completo (Ver HTML) Texto completo (Ver PDF)