Extreme Learning Machines for Data Classification Tuning by Improved Bat Algorithm

摘要: Single hidden layer feed forward neural networks are widely used for various practical problems. However, the training process determining synaptic weights of such can be computationally very expensive. In this paper we propose a new learning algorithm single feedforward in order to reduce time. We combining upgraded bat with extreme machine. The proposed approach reduces number evaluations needed train network and efficiently finds optimal input biases. was tested on standard benchmark classification problems functions compared other approaches from literature. results have shown that our produces satisfactory performance almost all cases it obtains solutions much faster than traditional algorithms.