.png){kind=icon}
返回
How to DODGE Complex Software Analytics
.png){kind=icon}
OA
AI
DOI：10.1109/TSE.2019.2945020.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine learning techniques applied to software engineering tasks can be improved by hyperparameter optimization, i.e., automatic tools that find good settings for a learner's control parameters. We show that such hyperparameter optimization can be unnecessarily slow, particularly when the optimizers waste time exploring redundant tunings, i.e., pairs of tunings which lead to indistinguishable results. By ignoring redundant tunings, DODGE(epsilon), a tuning tool, runs orders of magnitude faster, while also generating learners with more accurate predictions than seen in prior state-of-the-art approaches.
Keyword:
Tuning
Text mining
Software
Task analysis
Optimization
Software engineering
Tools
Software analytics
hyperparameter optimization
defect prediction
text mining
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.6
论文数:
2.8K
被引数:
1.1W
机构
引用论文
Microscale forced combustion: Pyrolysis-combustion flow calorimetry (PCFC)微尺度强制燃烧: 热解-燃烧流量量热法 (PCFC)
.png){kind=icon}
PREAI
分享收藏Tumor-induced endothelial cell apoptosis: Roles of NAD(P)H oxidase-derived reactive oxygen species
PREAI
分享收藏Las actitudes de los enfermeros de atención primaria en el ciclo de envejecimiento de las familias
OAAI
OAAI分享收藏Evolutionary Optimization of Software Quality Modeling with Multiple Repositories多知识库软件质量建模的进化优化
PREAI
分享收藏
查看更多内容