Mixed continuous/binary quantum-inspired learning system with non-negative least square optimisation for automated design of regularised ensemble extreme learning machines
This paper presents an improved particle swarm optimization (PSO) and discrete PSO (DPSO) with an enhancement operation by using a self-adaptive evolution strategies (ES). This improved PSO/DPSO is proposed for joint optimization of three-layer feedforward artificial neural network (ANN) structure and parameters (weights and bias), which is named ESPNet. The experimental results on two real-world problems show that ESPNet can produce compact ANNs with good generalization ability. r 2007 Elsevier B.V. All rights reserved.