Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet …
Abstract Model interpretability has become an important problem in machine learning (ML) due to the increased effect algorithmic decisions have on humans. Counterfactual …
O Bastani, C Kim, H Bastani - arXiv preprint arXiv:1705.08504, 2017 - arxiv.org
Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions. We propose to construct global explanations of complex …
O Bastani, C Kim, H Bastani - arXiv preprint arXiv:1706.09773, 2017 - arxiv.org
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach …
The expansion of machine learning to high-stakes application domains such as medicine, finance, and criminal justice, where making informed decisions requires clear understanding …
A Parmentier, T Vidal - International conference on machine …, 2021 - proceedings.mlr.press
Counterfactual explanations are usually generated through heuristics that are sensitive to the search's initial conditions. The absence of guarantees of performance and robustness …
BP Evans, B Xue, M Zhang - Proceedings of the genetic and evolutionary …, 2019 - dl.acm.org
Interpreting state-of-the-art machine learning algorithms can be difficult. For example, why does a complex ensemble predict a particular class? Existing approaches to interpretable …
J Hatwell, MM Gaber, RMA Azad - Artificial Intelligence Review, 2020 - Springer
Modern machine learning methods typically produce “black box” models that are opaque to interpretation. Yet, their demand has been increasing in the Human-in-the-Loop processes …
G Plumb, D Molitor… - Advances in neural …, 2018 - proceedings.neurips.cc
Abstract Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based …