The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery.

TL;DR: Transfer learning aims to improve the performance of target learners on target domains by transferring the knowledge contained in different but related source domains as discussed by the authors, in which the dependence on a large number of target-domain data can be reduced for constructing target learners.

TL;DR: This paper argues that the field of explainable artificial intelligence should build on existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics, and draws out some important findings.

TL;DR: In this paper, a taxonomy of recent contributions related to explainability of different machine learning models, including those aimed at explaining Deep Learning methods, is presented, and a second dedicated taxonomy is built and examined in detail.

TL;DR: In this paper, the authors provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box decision support systems, given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work.

TL;DR: This paper develops a novel, computationally efficient method called FAST for ranking all possible pairs of features as candidates for inclusion into the model, and shows the effectiveness of FAST in ranking candidate pairs of Features.

TL;DR: This study studies the performance of generalized additive models (GAMs), which combine single-feature models called shape functions through a linear function, and presents the first large-scale empirical comparison of existing methods for learning GAMs.

TL;DR: An empirical study is presented which investigates the suitability of a number of alternative representation formats for classification when interpretability is a key requirement and reveals a clear preference of users for decision tables in terms of ease of use.

TL;DR: The Bayesian Case Model (BCM) as discussed by the authors is a general framework for Bayesian case-based reasoning and prototype classification and clustering, which learns prototypes, the "quintessential" observations that best represent clusters in a dataset.