Memetic algorithms for training feedforward neural networks: an approach based on gravitational search algorithm
The backpropagation (BP) algorithm is a gradient-based algorithm used for training a feedforward neural network (FNN). Despite the fact that BP is still used today when FNNs are trained, it has some disadvantages, including the following: (i) it fails when non-differentiable functions are addressed,...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2020 |
| País: | España |
| Institución: | Universidad de Castilla-La Mancha |
| Repositorio: | RUIdeRA. Repositorio Institucional de la UCLM |
| OAI Identifier: | oai:ruidera.uclm.es:10578/30105 |
| Acceso en línea: | https://hdl.handle.net/10578/30105 |
| Access Level: | acceso abierto |
| Palabra clave: | Feedforward neural networks Memetic algorithms Gravitational search algorithm Quasi-Newton methods Redes neuronales de avance Algoritmos meméticos Algoritmo de búsqueda gravitacional Métodos Quasi-Newton |
| Sumario: | The backpropagation (BP) algorithm is a gradient-based algorithm used for training a feedforward neural network (FNN). Despite the fact that BP is still used today when FNNs are trained, it has some disadvantages, including the following: (i) it fails when non-differentiable functions are addressed, (ii) it can become trapped in local minima, and (iii) it has slow convergence. In order to solve some of these problems, metaheuristic algorithms have been used to train FNN. Although they have good exploration skills, they are not as good as gradient-based algorithms at exploitation tasks. The main contribution of this article lies in its application of novel memetic approaches based on the Gravitational Search Algorithm (GSA) and Chaotic Gravitational Search Algorithm (CGSA) algorithms, called respectively Memetic Gravitational Search Algorithm (MGSA) and Memetic Chaotic Gravitational Search Algorithm (MCGSA), to train FNNs in three classical benchmark problems: the XOR problem, the approximation of a continuous function, and classification tasks. The results show that both approaches constitute suitable alternatives for training FNNs, even improving on the performance of other state-of-the-art metaheuristic algorithms such as ParticleSwarm Optimization (PSO), the Genetic Algorithm (GA), the Adaptive Differential Evolution algorithm with Repaired crossover rate (Rcr-JADE), and the Covariance matrix learning and Bimodal distribution parameter setting Differential Evolution (COBIDE) algorithm. Swarm optimization, the genetic algorithm, the adaptive differential evolution algorithm with repaired crossover rate, and the covariance matrix learning and bimodal distribution parameter setting differential evolution algorithm. |
|---|