Delseny, Hervé, Gabreau, Christophe, Gauffriau, Adrien, Beaudouin, Bernard, Ponsolle, Ludovic, Alecu, Lucian, Bonnin, Hugues, Beltran, Brice, Duchel, Didier, Ginestet, Jean-Brice, Hervieu, Alexandre, Martinez, Ghilaine, Pasquet, Sylvain, Delmas, Kevin, Pagetti, Claire, Gabriel, Jean-Marc, Chapdelaine, Camille, Picard, Sylvaine, Damour, Mathieu, Cappi, Cyril, Gardès, Laurent, De Grancey, Florence, Jenn, Eric, Lefevre, Baptiste, Flandin, Gregory, Gerchinovitz, Sébastien, Mamalet, Franck, Albore, Alexandre
Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submitted to certification constraints. But what are the actual challenges? Can they be overcome by selecting appropriate ML techniques, or by adopting new engineering or certification practices? These are some of the questions addressed by the ML Certification 3 Workgroup (WG) set-up by the Institut de Recherche Technologique Saint Exup\'ery de Toulouse (IRT), as part of the DEEL Project.
There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence. We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles. This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data. This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Our findings suggest that the explanations derived from major algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous or even biased explanations. This paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable artificial intelligence.
A few years ago, when I was still working for IBM, I managed an AI project for a bank. During the final phase, my team and I went to the steering committee to present the results. Proud as the project leader, I have shown that the model has achieved 98 percent accuracy in detecting fraudulent transactions. In my manager's eyes, I could see a general panic when I explained that we used an artificial neural network, that it worked with a synapse system and weight adjustments. Although very efficient, there was no way to understand its logic objectively. Even if it was based on real facts, this raw explanation conditioned the project's continuity at that time, unless we could provide a full explanation that the senior executive could understand and trust.
A few years ago, when I was still working for IBM, I managed an AI project for a bank. During the final phase, my team and I went to the steering committee to present the results. Proud as the project leader, I have shown that the model has achieved 98 percent accuracy in detecting fraudulent transactions. In my manager's eyes, I could see a general panic when I explained that we used an artificial neural network, that it worked with a synapse system and weight adjustments. Although very efficient, there was no way to understand its logic objectively.
Recent applications of autonomous agents and robots, such as self-driving cars, scenario-based trainers, exploration robots, and service robots have brought attention to crucial trust-related challenges associated with the current generation of artificial intelligence (AI) systems. AI systems based on the connectionist deep learning neural network approach lack capabilities of explaining their decisions and actions to others, despite their great successes. Without symbolic interpretation capabilities, they are black boxes, which renders their decisions or actions opaque, making it difficult to trust them in safety-critical applications. The recent stance on the explainability of AI systems has witnessed several approaches on eXplainable Artificial Intelligence (XAI); however, most of the studies have focused on data-driven XAI systems applied in computational sciences. Studies addressing the increasingly pervasive goal-driven agents and robots are still missing. This paper reviews approaches on explainable goal-driven intelligent agents and robots, focusing on techniques for explaining and communicating agents perceptual functions (example, senses, and vision) and cognitive reasoning (example, beliefs, desires, intention, plans, and goals) with humans in the loop. The review highlights key strategies that emphasize transparency, understandability, and continual learning for explainability. Finally, the paper presents requirements for explainability and suggests a roadmap for the possible realization of effective goal-driven explainable agents and robots.
The lack of explainability of a decision from an Artificial Intelligence (AI) based "black box" system/model, despite its superiority in many real-world applications, is a key stumbling block for adopting AI in many high stakes applications of different domain or industry. While many popular Explainable Artificial Intelligence (XAI) methods or approaches are available to facilitate a human-friendly explanation of the decision, each has its own merits and demerits, with a plethora of open challenges. We demonstrate popular XAI methods with a mutual case study/task (i.e., credit default prediction), analyze for competitive advantages from multiple perspectives (e.g., local, global), provide meaningful insight on quantifying explainability, and recommend paths towards responsible or human-centered AI using XAI as a medium. Practitioners can use this work as a catalog to understand, compare, and correlate competitive advantages of popular XAI methods. In addition, this survey elicits future research directions towards responsible or human-centric AI systems, which is crucial to adopt AI in high stakes applications.
The remarkable advancements in Deep Learning (DL) algorithms have fueled enthusiasm for using Artificial Intelligence (AI) technologies in almost every domain; however, the opaqueness of these algorithms put a question mark on their applications in safety-critical systems. In this regard, the `explainability' dimension is not only essential to both explain the inner workings of black-box algorithms, but it also adds accountability and transparency dimensions that are of prime importance for regulators, consumers, and service providers. eXplainable Artificial Intelligence (XAI) is the set of techniques and methods to convert the so-called black-box AI algorithms to white-box algorithms, where the results achieved by these algorithms and the variables, parameters, and steps taken by the algorithm to reach the obtained results, are transparent and explainable. To complement the existing literature on XAI, in this paper, we take an `engineering' approach to illustrate the concepts of XAI. We discuss the stakeholders in XAI and describe the mathematical contours of XAI from engineering perspective. Then we take the autonomous car as a use-case and discuss the applications of XAI for its different components such as object detection, perception, control, action decision, and so on. This work is an exploratory study to identify new avenues of research in the field of XAI.
This has led to the development of a plethora of domain-dependent and context-specific methods for dealing with the interpretation of machine learning (ML) models and the formation of explanations for humans. Unfortunately, this trend is far from being over, with an abundance of knowledge in the field which is scattered and needs organisation. The goal of this article is to systematically review research works in the field of XAI and to try to define some boundaries in the field. From several hundreds of research articles focused on the concept of explainability, about 350 have been considered for review by using the following search methodology. In a first phase, Google Scholar was queried to find papers related to "explainable artificial intelligence", "explainable machine learning" and "interpretable machine learning". Subsequently, the bibliographic section of these articles was thoroughly examined to retrieve further relevant scientific studies. The first noticeable thing, as shown in figure 2 (a), is the distribution of the publication dates of selected research articles: sporadic in the 70s and 80s, receiving preliminary attention in the 90s, showing raising interest in 2000 and becoming a recognised body of knowledge after 2010. The first research concerned the development of an explanation-based system and its integration in a computer program designed to help doctors make diagnoses . Some of the more recent papers focus on work devoted to the clustering of methods for explainability, motivating the need for organising the XAI literature [4, 5, 6].
Explainable artificial intelligence (XAI) is the attempt to make the finding of results of non-linearly programmed systems transparent to avoid so-called black-box processes. The main task of XAI is to make non-linear programmed systems transparent. It offers practical methods to explain AI models, which, for example, correspond to the regulation of the General Data Protection Regulation (GDPR). The following five methods are listed, which have to make AI models more transparent and understandable. Layer-wise Relevance Propagation (LRP) is a technique that brings such explainability and scales to potentially highly complex deep neural networks.