Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Amina Adadi,Mohammed Berrada +1 more
Reads0
Chats0
TLDR
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.read more
Citations
More filters
Proceedings ArticleDOI
Mitigating Covertly Unsafe Text within Natural Language Systems
Alex Mei,Anisha Kabir,Sharon Levy,Melanie Subbiah,Emily Allaway,John Judge,Desmond Upton Patton,Bruce Bimber,Kathleen R. McKeown,William Yang Wang +9 more
TL;DR: This work distinguishes types of text that can lead to physical harm and establishes one particularly underexplored category: covertly unsafe text, which is further broken down with respect to the system’s information and discusses solutions to mitigate the generation of text in each of these subcategories.
Posted Content
Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery.
TL;DR: This work develops automated, natural language explanations for failures encountered during an AI agents' plan execution, and introduces a context-based information type for explanations that can both help non-expert users understand the underlying cause of a system failure, and select proper failure recoveries.
Journal ArticleDOI
SoK: Explainable Machine Learning for Computer Security Applications
TL;DR: This work systematizes the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks and presents an illustrative use case accentuating the role of model designers.
Proceedings ArticleDOI
A Teaching Language for Building Object Detection Models
TL;DR: This work proposes and assess an expressive teaching language for specifying object detectors which includes constructs such as concepts and relationships and applies these goals through a design probe that highlighted further research questions and a set of design takeaways.
Journal ArticleDOI
VisuaLizations As Intermediate Representations (VLAIR): An approach for applying deep learning-based computer vision to non-image-based data
TL;DR: VisuaLization As Intermediate Representation (VLAIR) as discussed by the authors was proposed to support accurate recognition in a number of fields while also enhancing humans' ability to interpret deep learning models for debugging purposes or for personal use.
References
More filters
Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Posted Content
Distilling the Knowledge in a Neural Network
TL;DR: This work shows that it can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model and introduces a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse.
Book ChapterDOI
Visualizing and Understanding Convolutional Networks
Matthew D. Zeiler,Rob Fergus +1 more
TL;DR: A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.
Proceedings ArticleDOI
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
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.
Journal ArticleDOI
Mastering the game of Go without human knowledge
David Silver,Julian Schrittwieser,Karen Simonyan,Ioannis Antonoglou,Aja Huang,Arthur Guez,Thomas Hubert,Lucas Baker,Matthew Lai,Adrian Bolton,Yutian Chen,Timothy P. Lillicrap,Fan Hui,Laurent Sifre,George van den Driessche,Thore Graepel,Demis Hassabis +16 more
TL;DR: An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.