Evolutionary Spiking Neural Networks for Solving Supervised Classification Problems
| Autor: | G. López-Vázquez, Manuel Ornelas-Rodríguez, Horacio Rostro-Gonzalez, Alfonso Rojas-Domínguez, Jorge A. Soria-Alcaraz, Hector J. Puga-Soberanes, Andrés Espinal, Juan Martín Carpio |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Article Subject
General Computer Science Computer science General Mathematics Feature vector Models Neurological Computer Science::Neural and Evolutionary Computation Action Potentials lcsh:Computer applications to medicine. Medical informatics lcsh:RC321-571 Grammatical evolution lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry Problem Solving Statistical hypothesis testing Neurons Spiking neural network Fitness function Artificial neural network business.industry General Neuroscience General Medicine Benchmark (computing) lcsh:R858-859.7 Neural Networks Computer Artificial intelligence business Algorithms Curse of dimensionality Research Article |
| Zdroj: | Computational Intelligence and Neuroscience Computational Intelligence and Neuroscience, Vol 2019 (2019) |
| ISSN: | 1687-5273 1687-5265 |
| Popis: | This paper presents a grammatical evolution (GE)-based methodology to automatically design third generation artificial neural networks (ANNs), also known as spiking neural networks (SNNs), for solving supervised classification problems. The proposal performs the SNN design by exploring the search space of three-layered feedforward topologies with configured synaptic connections (weights and delays) so that no explicit training is carried out. Besides, the designed SNNs have partial connections between input and hidden layers which may contribute to avoid redundancies and reduce the dimensionality of input feature vectors. The proposal was tested on several well-known benchmark datasets from the UCI repository and statistically compared against a similar design methodology for second generation ANNs and an adapted version of that methodology for SNNs; also, the results of the two methodologies and the proposed one were improved by changing the fitness function in the design process. The proposed methodology shows competitive and consistent results, and the statistical tests support the conclusion that the designs produced by the proposal perform better than those produced by other methodologies. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |