A continuation approach for training Artificial Neural Networks with meta-heuristics
| Autor: | Jairo Rojas-Delgado, Rafael Bello, Rafael A. Trujillo-Rasúa |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Fitness function
Optimization problem Artificial neural network Computer science business.industry Computer Science::Neural and Evolutionary Computation Particle swarm optimization 02 engineering and technology 01 natural sciences Artificial Intelligence 0103 physical sciences Signal Processing 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Firefly algorithm Computer Vision and Pattern Recognition Artificial intelligence 010306 general physics Cuckoo search business Metaheuristic Software |
| Zdroj: | Pattern Recognition Letters. 125:373-380 |
| ISSN: | 0167-8655 |
| DOI: | 10.1016/j.patrec.2019.05.017 |
| Popis: | Artificial Neural Networks research field is among the areas of major activity in Artificial Intelligence. Training a neural network is an NP-hard optimization problem that presents several theoretical and computational limitations. In optimization, continuation refers to an homotopy transformation of the fitness function that is used to obtain simpler versions of such fitness function and improve convergence. In this paper we propose an approach for Artificial Neural Network training based on optimization by continuation and meta-heuristic algorithms. The goal is to reduce overall execution time of training without causing negative effects in accuracy. We use continuation together with Particle Swarm Optimization, Firefly Algorithm and Cuckoo Search for training neural networks on public benchmark datasets. The continuation variations of the studied meta-heuristic algorithms reduce execution time required to complete training in about 5–30% without statistically significant loss of accuracy when compared with standard variations of the meta-heuristics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect