An Evolutionary Extreme Learning Machine based on Fuzzy Fish Swarms

摘要

Neural networks have been largely applied into many real world pattern classification problems. During the training phase, every neural network can suffer from generalization loss caused by overfitting, thereby the process of learning is highly biased. In this work we propose an Adaptive Modified Artificial Fish Swarm Algorithm applied to the optimization of Extreme Learning Machines. The algorithm presents the basic Artificial Fish Swarm Algorithm (AFSA) with some features from Differential Evolution (Crossover and Mutation) and fuzzy rules to improve the quality of the solutions during the search process. The results of the simulations demonstrated good generalization capacity from the best individuals obtained in the training phase.