Particle swarm optimization based extreme learning neuro-fuzzy system for regression and classification

•Improves regularized fuzzy-neuro system using optimization.•Regularization parameter is tuned by particle swarm optimization.•Shows that proposed technique gives the best generalization performance. This paper improves the performance of adaptive neuro-fuzzy inference system (ANFIS) using extreme learning machines (ELM) concept and particle swarm optimization (PSO). The proposed learning machine, particle swarm optimization (PSO) based regularized extreme learning adaptive neuro-fuzzy inference system (PSO-RELANFIS), has the advantages of reduced randomness, reduced computational complexity and better generalization. The fuzzy membership function parameters of the proposed system are randomly selected with in constraint ranges. A regularized loss function is developed using constrained optimization and the optimized regularization parameter is obtained using PSO technique. Performance analysis on regression and classification problems shows that proposed algorithm achieves similar or better generalization performance compared to well-known kernel based methods and ELM based neuro-fuzzy systems.