Evento
Symmetric Simplicial Neural Networks
Tipo del evento:
Conferencia
Nombre del evento:
55th Annual Conference on Information Sciences and Systems (CISS)
Fecha del evento:
24/03/2021
Institución Organizadora:
Institute of Electrical and Electronics Engineers;
Título del Libro:
2021 55th Annual Conference on Information Sciences and Systems (CISS)
Editorial:
Institute of Electrical and Electronics Engineers
ISBN:
978-1-6654-4844-4
Idioma:
Inglés
Clasificación temática:
Resumen
Convolutional Neural Networks are capable of per- form many complex tasks such as image classification. Recently morphological functions where introduced as a replacement of the first convolutional layers in any net, using their non-linearities to achieve better accuracy for classification Neural Networks, but in most cases the functions are fixed beforehand and can not be trained. We propose the use of Symmetric Simplicial algorithm that can be trained to perform many morphological computations and even more complex functions. We present the training of a certain topology that uses Symmetric Simplicials instead of morphological functions and the classification accuracy achieved during the training process.
Archivos asociados
Licencia
Identificadores
Colecciones
Eventos(IIIE)
Eventos de INST.DE INVEST.EN ING.ELECTRICA "A.DESAGES"
Eventos de INST.DE INVEST.EN ING.ELECTRICA "A.DESAGES"
Citación
Symmetric Simplicial Neural Networks; 55th Annual Conference on Information Sciences and Systems (CISS); Baltimore; Estados Unidos; 2021; 1-6
Compartir