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
Book ChapterDOI
Explainability and Interpretability: Keys to Deep Medicine
TL;DR: The success of intelligent solutions in health and medicine depends on the degree to which they support interoperability, to allow consistent integration of different systems and data sources, and explainability to make their decisions understandable, interpretable, and justifiable by humans as discussed by the authors.
Journal ArticleDOI
Explaining CNN and RNN Using Selective Layer-Wise Relevance Propagation
TL;DR: In this paper, the authors proposed a selective layer-wise relevance propagation (LSRP) which produces a clearer heatmap than the existing methods by combining relevance-based methods and gradientbased methods.
Journal ArticleDOI
Towards Industrial Revolution 5.0 and Explainable Artificial Intelligence: Challenges and Opportunities
Imran Taj,Nz Jhanjhi +1 more
TL;DR: In this paper, the authors reviewed the enabling technologies for Industry 5.0 and suggested some pertinent research areas requiring more focus and highlighted hot research spots that will eventually fill in the gaps within societal domains.
Journal ArticleDOI
What is it about humanity that we can’t give away to intelligent machines? A European perspective
Crispin Coombs,Patrick Stacey,Peter Kawalek,Boyka Simeonova,Jörg Becker,Katrin Bergener,João Álvaro Carvalho,Marcelo Fantinato,Niels Frederik Garmann-Johnsen,Christian Grimme,Armin Stein,Heike Trautmann +11 more
TL;DR: In this article, the authors report the findings of a workshop that investigated the application of the principles of human freedom throughout intelligent machine development and use and provide an agenda for future AI and humanity research.
Journal ArticleDOI
Neural Collapse: A Review on Modelling Principles and Generalization
TL;DR: This work analyzes the principles which aid in modelling such a phenomena from the ground up and shows how they can build a common understanding of the recently proposed models that try to explain NC.
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.