BriefGPT.xyz
Feb, 2020
用于可解释性的生成可证明近似最优的聚类描述符的高效算法
Efficient Algorithms for Generating Provably Near-Optimal Cluster Descriptors for Explainability
HTML
PDF
Prathyush Sambaturu, Aparna Gupta, Ian Davidson, S. S. Ravi, Anil Vullikanti...
TL;DR
本文研究如何提高机器学习方法结果的可解释性，探讨了通过构建对聚类进行简洁表示的方法，提出了可证明性能保证的近似算法，并应用于基因组序列的不同威胁级别的聚类解释。
Abstract
Improving the
explainability
of the results from
machine learning
methods has become an important research goal. Here, we study the problem of making
→