In this work, we propose a novel evolutionary algorithm for neural architecture search, applicable to global search spaces. The algorithm's architectural representation organizes the topology in multiple hierarchical modules, while the design process exploits this representation, in order to explore the search space. We also employ a curation system, which promotes the utilization of well performing sub-structures to subsequent generations. We apply our method to Fashion-MNIST and NAS-Bench101, achieving accuracies of $93.2\%$ and $94.8\%$ respectively in a relatively small number of generations.
翻译:在这项工作中,我们提出了适用于全球搜索空间的神经结构搜索新进化算法,该算法的建筑代表性将地形学组织成多个等级模块,而设计过程则利用这一结构来探索搜索空间。我们还采用了一种分类系统,促进后代人利用运作良好的次级结构。我们采用的方法是时尚-MNIST和NAS-Bench101,在相对较少的几代人中分别达到93.2美元和94.8美元。