A Stage-Specific Gene Expression Framework for Promoting Genetic Algorithm

Genetic algorithm (GA) has become very popular for tackling computationally expensive numerical optimization problems. To optimize their performance and convergence rate, we propose demonstrate an embedded stage-specific gene expression framework (SGEF) with a two-tier coding scheme filter operator based on variational auto-encoder. For the first time, structure of auto-encoder is used to map parent population genetic from uniformly distributed high dimensions Gaussian low dimensions. The design which can maintain trade-off balance between exploitation exploration also analyzed in detail. experimental results demonstrated good proposed SGEF promoting both single-objective algorithms multiple-objective algorithms.