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
Does BERT Pay Attention to Cyberbullying
TL;DR: This paper examined the use of BERT for cyberbullying detection on various datasets and attempt to explain its performance by analyzing its attention weights and gradient-based feature importance scores for textual and linguistic features.
Journal ArticleDOI
Augmented intelligence in pediatric anesthesia and pediatric critical care.
TL;DR: Acute care technologies, including novel monitoring devices, big data, increased computing capabilities, machine-learning algorithms and automation, are converging, enabling the application of augmented intelligence for improved outcome predictions, clinical decision-making, and offers unprecedented opportunities to improve patient outcomes, reduce costs, and improve clinician workflow.
Journal ArticleDOI
Technical Note: Temporal disaggregation of spatial rainfall fields with generative adversarial networks
TL;DR: Limitations that are found are that providing additional input to the GAN surprisingly leads to worse results, showing that it is not trivial to increase the amount of used input information, and that expert judgment is still needed to determine at which point the training should stop, because longer training leads to better results.
Book ChapterDOI
The AIQ Meta-Testbed: Pragmatically Bridging Academic AI Testing and Industrial Q Needs
TL;DR: The AIQ Meta-Testbed as mentioned in this paper is a meta-testbed for quality assurance of artificial intelligence applications with a focus on automated testing and verification. But there is no consensus on what artificial intelligence means and interpretations range from simple statistical analysis to sentient humanoid robots.
Journal ArticleDOI
Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
Shaukat Ali,Tamer AbuHmed,Shaker El-Sappagh,Khan Muhammad,J. Alonso-Moral,Roberto Confalonieri,Riccardo Guidotti,Javier Del Ser,Natalia Díaz-Rodríguez,Francisco Herrera +9 more
TL;DR: XAI has become a popular research subject within the AI field in recent years as discussed by the authors , and the need for eXplainable AI (XAI) methods for improving trust in AI models has arisen.
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.