Abstract
In this paper, an adaptive evolutionary multi-objective selection method of REF Networks structure is discussed. The candidates of REF Network structures are encoded into particles in Particle Swarm Optimization (PSO). These particles evolve toward Pareto-optimal front defined by several objective functions with model accuracy and complexity. The problem of unsupervised and supervised learning is discussed with Adaptive Multi-Objective PSO (AMOPSO). This study suggests an approach of REF Network training through simultaneous optimization of architectures and weights with Adaptive PSO-based multi-objective algorithm. Our goal is to determine whether Adaptive Multi-objective PSO can train REF Networks, and the performance is validated on accuracy and complexity. The experiments are conducted on two benchmark datasets obtained from the machine learning repository. The results show that our proposed method provides an effective means for training REF Networks that is competitive with PSO-based multi-objective algorithm.