ERNEAD: Training of Artificial Neural Networks Based on a Genetic Algorithm and Finite Automata Theory
Fecha
2018
2018
Autor
Ruiz-Rangel, Jonathan
Ardila Hernandez, Carlos Julio
Maradei Gonzalez, Luis
Jabba Molinares, Daladier
Metadatos
Mostrar el registro completo del ítem
Mostrar el registro completo del ítem
Resumen
This paper presents a variation in the algorithm EMODS (Evolutionary Metaheuristic of Deterministic Swapping), at the level of its mutation stage in order to train algorithms for each problem. It should be noted that the EMODS metaheuristic is a novel framework that allows multi-objective optimization of combinatorial problems. The proposal for the training of neural networks will be named ERNEAD (training of Evolutionary Neural Networks through Evolutionary Strategies and Finite Automata). The selection process consists of five phases: the initial population generation phase, the forward feeding phase of the network, the EMODS search phase, the crossing and evaluation phase, and finally the verification phase. The application of the process in the neural networks will generate sets of networks with optimal weights for a particular problem. ERNEAD algorithm was applied to two typical problems: breast cancer and flower classification, the solution of the problems were compared with solutions obtained by applying the classical Backpropagation, Conjugate Gradient and Levenberg-Marquardt algorithms. The analysis of the results indicated that ERNEAD produced more precise solutions than the ones thrown by the classic algorithms.
Enlace para referencia:
http://hdl.handle.net/20.500.12442/1863
http://hdl.handle.net/20.500.12442/1863
Enlace al recurso externo:
http://www.ceser.in/ceserp/index.php/ijai/article/view/5456
http://www.ceser.in/ceserp/index.php/ijai/article/view/5456
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Water cycle algorithm: implementation and analysis of solutions to the bi-bjective travelling salesman problem
Pimentel, Jairo; Ardila Hernandez, Carlos Julio; Niño, Elías; Jabba Molinares, Daladier; Ruiz-Rangel, Jonathan (International Journal of Artificial Intelligence, 2019)This research is an implementation of the Water Cycle Algorithm (WCA) to solve the biobjective Travelling Salesman Problem, based on the kroAB100 problem in the TSPLIB library, and compare its performance to an alternative ... -
Conditioning of extreme learning machine for noisy data using heuristic optimization
Salazar, E; Mora, M; Vásquez, A; Gelvez, E (IOP Publishing, 2020)This article provides a tool that can be used in the exact sciences to obtain good approximations to reality when noisy data is inevitable. Two heuristic optimization algorithms are implemented: Simulated Annealing and ... -
GeoGebra as learning tool for the search of the roots of functions in numerical methods
Arceo-Díaz, S; Briceo Barrios, E E; Aréchiga Maravillas, J; Salazar-Torres, J (IOP Publishing, 2020)Physics is capable of describing, through equations, phenomena on a micro and macroscopic scale. However, most of these equations are non-linear and the identification of their roots requires the use of approximation ...