当前位置: X-MOL 学术arXiv.cs.NE › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Novel Evolutionary Algorithm for Hierarchical Neural Architecture Search
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2021-07-18 , DOI: arxiv-2107.08484
Aristeidis Chrostoforidis, George Kyriakides, Konstantinos Margaritis

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.

中文翻译:

一种用于分层神经架构搜索的新进化算法

在这项工作中,我们提出了一种适用于全局搜索空间的新型神经架构搜索进化算法。该算法的架构表示在多个层次模块中组织拓扑,而设计过程利用这种表示来探索搜索空间。我们还采用了一个策展系统,该系统将性能良好的子结构的利用推广到后代。我们将我们的方法应用于 Fashion-MNIST 和 NAS-Bench101,在相对较少的世代中分别实现了 $93.2\%$ 和 $94.8\%$ 的准确率。
更新日期:2021-07-20
down
wechat
bug