Autores
Argüelles Cruz Amadeo José
López Yáñez Itzamá
Aldape Pérez Mario
Título Alpha-Beta Weightless Neural Networks
Tipo Congreso
Sub-tipo SCOPUS
Descripción Lecture Notes in Computer Science
Resumen A novel weightless neural network model is presented, based on the known operations Alpha and Beta, and three original operations proposed. The new model of weightless neural network has been called CAINN – Computing Artificial Intelligent Neural Network. The experimental aspect is presented by applying the CAINN model to several known databases. Also, comparative studies about the performance of the CAINN model concerning ADAM weightless neural network and other models are reported. Results exhibit the superiority of the CAINN model over the ADAM model, its counterpart as a weightless neural network; and over other models immersed in the state of the art of neural networks; taking into account the No Free Lunch theorem.
Observaciones 13th Iberoamerican Congress on Pattern Recognition, CIARP 2008; Code 74234; ISBN: 3540859195;978-354085919-2
Lugar Havana
País Cuba
No. de páginas 496-503
Vol. / Cap. 5197
Inicio 2008-09-09
Fin 2008-09-12
ISBN/ISSN 3540859195;978-35408