Transcription of Anchors: High Precision Model-Agnostic Explanations
{{id}} {{{paragraph}}}
Example: bachelor of science
Anchors: High Precision Model-Agnostic Explanations
Anchors: High- Precision Model-Agnostic ExplanationsMarco Tulio RibeiroUniversity of SinghUniversity of California, GuestrinUniversity of introduce a novel Model-Agnostic system that explains thebehavior of complex models with high- Precision rules calledanchors, representing local, sufficient conditions for predic-tions. We propose an algorithm to efficiently compute theseexplanations for any black-box model with high-probabilityguarantees. We demonstrate the flexibility of anchors by ex-plaining a myriad of different models for different domainsand tasks. In a user study, we show that anchors enable usersto predict how a model would behave on unseen instanceswith less effort and higher Precision , as compared to existinglinear Explanations or no machine learning models such as deep neuralnetworks have been shown to be highly accurate for manyapplications, even though their complexity virtually makesthem black-boxes. As a consequence of the need for usersto understand the behavior of these models,interpretablemachine learninghas seen a resurgence in recent years,ranging from the design of novelglobally-interpretable ma-chine learning models (Lakkaraju, Bach, and Leskovec 2016;Ustun and Rudin 2015; Wang and Rudin 2015) to local ex-planations (for individual predictions) that can be computedfor any classifier (Baehrens et ; Ribeiro, Singh, andGuestrin 2016b; Strumbelj and Kononenko 2010).
strate that the model is picking up on reasonable patterns of the English language, e.g. if play is preceded by a determiner, it is likely used as a noun. In Table 2, we compute anchors for a multi-layer RNN encoder/attention-based decoder translation system (Vinyals et al. 2015) trained on English-Portuguese parallel corpora. In
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: