Artículo
Optimum Integration Procedure for Connectionist and Dynamic Field Equations
Fecha de publicación:
05/2021
Editorial:
Frontiers Media
Revista:
Frontiers in Neurorobotics
ISSN:
1662-5218
Idioma:
Inglés
Tipo de recurso:
Artículo publicado
Clasificación temática:
Resumen
Connectionist and dynamic field models consist of a set of coupled first-order differential equations describing the evolution in time of different units. We compare three numerical methods for the integration of these equations: the Euler method, and two methods we have developed and present here: a modified version of the fourth-order Runge Kutta method, and one semi-analytical method. We apply them to solve a well-known nonlinear connectionist model of retrieval in single-digit multiplication, and show that, in many regimes, the semi-analytical and modified Runge Kutta methods outperform the Euler method, in some regimes by more than three orders of magnitude. Given the outstanding difference in execution time of the methods, and that the EM is widely used, we conclude that the researchers in the field can greatly benefit from our analysis and developed methods.
Archivos asociados
Licencia
Identificadores
Colecciones
Articulos(INCYT)
Articulos de INSTITUTO DE NEUROCIENCIAS COGNITIVAS Y TRASLACIONAL
Articulos de INSTITUTO DE NEUROCIENCIAS COGNITIVAS Y TRASLACIONAL
Citación
Rieznik, Andrés Anibal; Di Tella, Rocco; Schvartzman, Lara; Babino, Andrés; Optimum Integration Procedure for Connectionist and Dynamic Field Equations; Frontiers Media; Frontiers in Neurorobotics; 15; 5-2021; 1-6
Compartir
Altmétricas