Algorithms for interpretable machine learning

By Cynthia Rudin. 2014

70 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Interpretability via Model Extraction (2017, background): “Interpretability is a promising approach to address these challenges [12, 24]—we can help human users diagnose issues and verify correctness of machine learning models by providing insight into the model’s reasoning [3, 18, 20, 23, 26].”
Increasing Trust in AI Services through Supplier's Declarations of Conformity (2018, background): “Explainability Directly interpretable machine learning (in contrast to post hoc interpretation) [38], in which a person can look at a model and understand what it does, reduces epistemic uncertainty and increases safety because quirks and vagaries of training dataset distributions that will not be…”
Interpreting Blackbox Models via Model Extraction (2017, background): “Interpretability is a promising approach to address these challenges [38, 21]—in particular, we can help human users diagnose issues and verify correctness of machine learning models by providing insight into the model’s reasoning [43, 8, 37, 31, 29].”
A Nutritional Label for Rankings (2018, background): “With the exception of recent machine learning results that enable interpretability of particular classes of algorithms [6, 7, 12], recent scholarship on algorithmic accountability has primarily focused on enabling an analyst to retroactively verify particular properties rather than proactively expos”
Explaining Explanations to Society (2019, background): “Although there have been calls for work on creating systems and algorithms that can interpret [7, 27] and explain [12] some parts of their decisions, the current state-of-the-art explanatory systems are made for the programmer or expert, not an end user or policy-maker.”
Data Science of the People , for the People , by the People : A Viewpoint on an Emerging Dichotomy (2015, unknown): “the model should be interpretable for the people [23, 41].”
FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity. (2018, background): “[44] C.”
FactSheets: Increasing trust in AI services through supplier's declarations of conformity (2019, background): “Explainability: Directly interpretable machine learning (in contrast to post hoc interpretation) [44], in which a person can look at a model and understand what it does, reduces epistemic uncertainty and increases safety because quirks and vagaries of training dataset distributions that will not be…”
Interpretable Policies for Dynamic Product Recommendations (2016, background): “Lack of interpretable solutions can be an important road-block in many critical domains, such as medicine [12, 11, 26].”
Interpretable Machine Learning : Lessons from Topic Modeling (2016, background): “However, experts in these domains are unlikely to widely adopt machine learning tools if they do not understand or trust these tools [22] [5].”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “is prominently due to the fast increase in the popularity of ML and in particular of deep learning (DL), with many applications in several business areas, spanning from e-commerce [7] to games [8] and including applications in criminal justice [9, 10], healthcare [11], computer vision [10]”
Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems (2018, methodology): “…groups have developed techniques intended to improve machine learning systems’ interpretability (Zhang & Zhu, 2018; Guidotti et al., 2018; Chakraborty et al., 2017; Rudin, 2014), though the deﬁni-tions of and motivations for interpretability (if speciﬁed) vary wildly between methods (Lipton, 2016).”
Learning Multi-Way Relations via Tensor Decomposition With Neural Networks (2018, background): “In addition, interpretability as well as prediction performance is becoming more important nowadays with the widening of machine-learning applications (Rudin 2014; Lipton 2016).”