Learning-aided Evolution for Optimization

Learning and optimization are the two essential abilities of human beings for problem solving. Similarly, computer scientists have made great efforts to design artificial neural network (ANN) evolutionary computation (EC) simulate learning ability solving real-world problems, respectively. These been branches in intelligence (AI) science. However, humans, usually integrated together Therefore, how efficiently integrate these develop powerful AI remains a significant but challenging issue. Motivated by this, this paper proposes novel learning-aided (LEO) framework that plus evolution problems. The LEO is with knowledge learned ANN from process EC promote efficiency. applied both classical algorithms some state-of-the-art including champion algorithm, benchmarking against IEEE Congress on Evolutionary Computation competition data. experimental results show can significantly enhance existing better solve single-objective multi-/many-objective global suggesting more intelligent Moreover, also validated time efficiency LEO, where additional cost using greatly deserved. promising lead new efficient paradigm problems evolution.