Code underlying the PhD thesis: Efficient Evolutionary Hyperparameter Optimization for Deep Learning

Code underlying the PhD thesis: Efficient Evolutionary Hyperparameter Optimization for Deep Learning. As the focus of the thesis is on hyperparameter optimization, code for the algorithms developed during the PhD research are included, namely ENCAS, PBT-NAS, IPBT, HyFree-S3, as well as code for comparing and evaluating previously existing PBT variants. A general readme file is included, as well as code directories, one per chapter/project, each containing its own readme file with instructions on reproducing the experiments.本数据集为博士论文《面向深度学习的高效进化式超参数优化》（Efficient Evolutionary Hyperparameter Optimization for Deep Learning）的配套代码。鉴于本论文的核心研究方向为超参数优化，数据集收录了博士研究期间开发的多款算法代码，具体包括ENCAS、PBT-NAS、IPBT、HyFree-S3，同时包含用于对比与评估现有PBT变体的代码。数据集附带通用说明文档，同时按章节或项目划分代码目录，每个目录均配有独立的说明文件，其中包含实验复现的详细操作指引。