13 citations · 21 across the 4 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2019★ 13 cited
A study of data and label shift in the LIME framework
Amir Hossein Akhavan Rahnama, Henrik Boström
LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate…
stat.ML2016★ 1 cited
Clustering with Confidence: Finding Clusters with Statistical Guarantees
Andreas Henelius, Kai Puolamäki, Henrik Boström +1
Clustering is a widely used unsupervised learning method for finding structure in the data. However, the resulting clusters are typically presented without any guarantees on their…