A cooperative genetic algorithm based on extreme learning machine for data classification

It is a challenging task to optimize network structure and connection parameters simultaneously in a single hidden layer feedforward neural network (SLFN). Extreme learning machine (ELM) is a popular non-iterative learning method in recent years, which often provides good generalization performance of a SLFN at extremely fast learning speed, yet only for fixed network structure. In this work, a cooperative binary-real genetic algorithm (CGA) based on ELM, called CGA-ELM, is proposed to adjust the structure and parameters of a SLFN simultaneously for achieving a compact network with good generalization performance. In CGA-ELM, a hybrid coding scheme is designed to evolve the network structure and input parameters, i.e., input weights between input nodes and hidden nodes as well as the biases of hidden nodes. Then output parameters, i.e., output weights between hidden nodes and output nodes, are determined by the ELM. A combination of training error and network complexity is taken as the fitness function to evaluate the performance of a SLFN. A binary GA is responsible for optimizing network structure, while a real GA and the ELM optimize collaboratively network parameters. Experimental results on classification applications demonstrate that CGA-ELM outperforms CGA and ELM significantly in terms of the generalization ability. Also, CGA-ELM has more competitive capacity when compared with other state-of-the-art algorithms.

Automated summary

This study proposes a CGA-ELM method based on ELM to simultaneously adjust the structure and parameters of a SLFN. By designing a hybrid coding scheme, the network structure and input parameters can be evolved and the output parameters can be determined using ELM. Experimental results demonstrate that CGA-ELM outperforms CGA and ELM significantly in terms of generalization ability, and has more competitive capacity.