151 citations · 692 across the 40 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
stat.ML2016★ 36 cited
Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable
Sarah Tan, Matvey Soloviev, Giles Hooker +1
Ensembles of decision trees perform well on many problems, but are not interpretable. In contrast to existing approaches in interpretability that focus on explaining relationships…
stat.ME2016★ 40 cited
Interpreting Models via Single Tree Approximation
Yichen Zhou, Giles Hooker
We propose a procedure to build a decision tree which approximates the performance of complex machine learning models. This single approximation tree can be used to interpret and s…