首页|Study Findings from Open University Broaden Understanding of Machine Learning (E stimating the Replication Probability of Significant Classification Benchmark Ex periments)
Study Findings from Open University Broaden Understanding of Machine Learning (E stimating the Replication Probability of Significant Classification Benchmark Ex periments)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Current study results on Machine Learn ing have been published. According to newsoriginating from Milton Keynes, Unite d Kingdom, by NewsRx editors, the research stated, “A fundamentalquestion in ma chine learning is: ‘What are the chances that a statistically significant result will replicate?’The standard framework of null hypothesis significance testing , however, cannot answer this questiondirectly. In this work, we derive formula s for estimating the replication probability that are applicable intwo of the m ost widely used experimental designs in machine learning: the comparison of two classifiersover multiple benchmark datasets and the comparison of two classifie rs in k-fold cross-validation.”
Milton KeynesUnited KingdomEuropeC yborgsEmerging TechnologiesMachine LearningOpen University
NETL
NSTL
