Print Email Facebook Twitter Interpretability and performance of surrogate decision trees produced by Viper Title Interpretability and performance of surrogate decision trees produced by Viper Author Kaaij, Otto (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Lukina, A. (mentor) Murukannaiah, P.K. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-01-28 Abstract Machine learning models are being used extensively in many high impact scenarios. Many of these models are ‘black boxes’, which are almost impossible to interpret. Successful implementations have been limited by this lack of interpretability. One approach to increasing interpretability is to use imitation learning to extract a more interpretable surrogate model from a black box model. Our aim is to evaluate Viper, an imitation learning algorithm, in terms of performance and interpretability. To achieve this, we evaluate surrogate decision tree models produced by Viper on three different environments and attempt to interpret these models. We find that Viper generally produces high performance interpretable decision trees, and that performance and interpretability are highly dependent on context and oracle quality. We compare Viper performance to similarimitation learning approaches, and find that it performs as good as or better than these approaches, though our comparison is limited by the differences in oracle quality. Subject InterpretabilityViperImitation LearningSurrogate modelsXAI To reference this document use: http://resolver.tudelft.nl/uuid:a090bdca-e681-42b6-a099-7cd546ec467b Part of collection Student theses Document type bachelor thesis Rights © 2022 Otto Kaaij Files PDF ViperInterpretability.pdf 518.23 KB Close viewer /islandora/object/uuid:a090bdca-e681-42b6-a099-7cd546ec467b/datastream/OBJ/view