Principles of Explanatory Debugging to Personalize Interactive Machine Learning.
IUI(2015)
摘要
ABSTRACTHow can end users efficiently influence the predictions that machine learning systems make on their behalf? This paper presents Explanatory Debugging, an approach in which the system explains to users how it made each of its predictions, and the user then explains any necessary corrections back to the learning system. We present the principles underlying this approach and a prototype instantiating it. An empirical evaluation shows that Explanatory Debugging increased participants' understanding of the learning system by 52% and allowed participants to correct its mistakes up to twice as efficiently as participants using a traditional learning system.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络