Posted Content•
Towards A Rigorous Science of Interpretable Machine Learning
TL;DR: This position paper defines interpretability and describes when interpretability is needed (and when it is not), and suggests a taxonomy for rigorous evaluation and exposes open questions towards a more rigorous science of interpretable machine learning.
Abstract: As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.
Citations
More filters
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.
2,827 citations
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.
Abstract: In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. 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. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.
2,805 citations
SIDI1
TL;DR: This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI, and review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.
Abstract: At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.
2,258 citations
Cites background from "Towards A Rigorous Science of Inter..."
...Available: https://christophm.github.io/interpretable-ml-book/ [106] O. Bastani, C. Kim, and H. Bastani....
[...]
...Available: https://sites.google.com/view/whi2018/ [6] A. G. Wilson, B. Kim, and W. Herlands....
[...]
...Doshi-Velez and Kim established a baseline of evaluation approaches and proposed three major types of interpretability evaluation: (i) application-grounded: put the explanation into the application and let the end user (typically a domain expert) test it....
[...]
...Most research works on the ML interpretability agreed and contribute towards more rigorous notion of interpretability [62]....
[...]
...[134] B. Kim, C. Rudin, and J. A. Shah, ‘‘The Bayesian case model: A generative approach for case-based reasoning and prototype classification,’’ in Proc....
[...]
Posted Content•
TL;DR: Previous efforts to define explainability in Machine Learning are summarized, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought, and a taxonomy of recent contributions related to the explainability of different Machine Learning models are proposed.
Abstract: In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
1,602 citations
Posted Content•
TL;DR: SmoothGrad is introduced, a simple method that can help visually sharpen gradient-based sensitivity maps and lessons in the visualization of these maps are discussed.
Abstract: Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of the class score function with respect to the input image. This gradient can be interpreted as a sensitivity map, and there are several techniques that elaborate on this basic idea. This paper makes two contributions: it introduces SmoothGrad, a simple method that can help visually sharpen gradient-based sensitivity maps, and it discusses lessons in the visualization of these maps. We publish the code for our experiments and a website with our results.
1,477 citations
References
More filters
TL;DR: Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
Abstract: The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.
14,377 citations
"Towards A Rigorous Science of Inter..." refers background in this paper
...…to predictive policing systems, machine learning (ML) systems are increasingly ubiquitous; they outperform humans on specific tasks [Mnih et al., 2013, Silver et al., 2016, Hamill, 2017] and often guide processes of human understanding and decisions [Carton et al., 2016, Doshi-Velez et al., 2014]....
[...]
01 Jan 1998
12,940 citations
"Towards A Rigorous Science of Inter..." refers background in this paper
...Just as there are now large open repositories for problems in classification, regression, and reinforcement learning [Blake and Merz, 1998, Brockman et al., 2016, Vanschoren et al., 2014], we advocate for the creation of repositories that contain problems corresponding to real-world tasks in which…...
[...]
13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Abstract: Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally varound the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.
11,104 citations
Posted Content•
TL;DR: This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Abstract: We present the first deep learning model to successfully learn control
policies directly from high-dimensional sensory input using reinforcement
learning. The model is a convolutional neural network, trained with a variant
of Q-learning, whose input is raw pixels and whose output is a value function
estimating future rewards. We apply our method to seven Atari 2600 games from
the Arcade Learning Environment, with no adjustment of the architecture or
learning algorithm. We find that it outperforms all previous approaches on six
of the games and surpasses a human expert on three of them.
8,757 citations
"Towards A Rigorous Science of Inter..." refers background in this paper
...…email-filters to predictive policing systems, machine learning (ML) systems are increasingly ubiquitous; they outperform humans on specific tasks [Mnih et al., 2013, Silver et al., 2016, Hamill, 2017] and often guide processes of human understanding and decisions [Carton et al., 2016,…...
[...]
Proceedings Article•
05 Dec 2016TL;DR: This work proposes a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features and shows how to optimally adjust any learned predictor so as to remove discrimination according to this definition.
Abstract: We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. We enourage readers to consult the more complete manuscript on the arXiv.
2,690 citations
"Towards A Rigorous Science of Inter..." refers background in this paper
...…criteria such as safety [Otte, 2013, Amodei et al., 2016, Varshney and Alemzadeh, 2016], nondiscrimination [Bostrom and Yudkowsky, 2014, Ruggieri et al., 2010, Hardt et al., 2016], avoiding technical debt [Sculley et al., 2015], or providing the right to explanation [Goodman and Flaxman, 2016]....
[...]
...• Multi-objective trade-offs: Two well-defined desiderata in ML systems may compete with each other, such as privacy and prediction quality [Hardt et al., 2016] or privacy and nondiscrimination [Strahilevitz, 2008]....
[...]