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
Journal ArticleDOI
Towards a mathematical framework to inform neural network modelling via polynomial regression.
TL;DR: In this article, a mathematical framework relating neural networks and polynomial regression is explored by building an explicit expression for the coefficients of a linear regression from the weights of a given neural network, using a Taylor expansion approach.
Book ChapterDOI
Constructing Interpretable Decision Trees Using Parallel Coordinates
TL;DR: In this paper, a new type of oblique rule for decision tree classifiers that is interpretable to human users has been proposed, and the use of an evolutionary algorithm has been used to learn this new rule and show that it produces significantly smaller trees compared to a tree created with axis-parallel rules.
Posted ContentDOI
Comparison of Attention-based Deep LearningModels for EEG Classification
Giulia Cisotto,Alessio Zanga,Joanna Chlebus,Italo Zoppis,Sara Manzoni,Urszula Markowska-Kaczmar +5 more
TL;DR: Attention represents a promising strategy to evaluate the quality of the EEG information, and its relevance, in different real-world scenarios and can make it easier to parallelize the computation and, thus, to speed up the analysis of big electrophysiological datasets.
Journal ArticleDOI
Explainable artificial intelligence for building energy performance certificate labelling classification
TL;DR: In this article , the authors proposed an alternative approach to classify a building's EPC label using artificial neural network (ANN) models, which can achieve a 99% precision with sufficient input data.
Journal ArticleDOI
Updates in deep learning research in ophthalmology.
Wei Yan Ng,Shihao Zhang,Zhaoran Wang,Charles Jit Teng Ong,Dinesh Visva Gunasekeran,Gilbert Lim,Feihui Zheng,Shaun Chern Yuan Tan,Gavin Tan,Tyler Hyungtaek Rim,Leopold Schmetterer,Daniel Shu Wei Ting +11 more
TL;DR: In this article, a combination of factors including concerns over security and privacy, poor generalizability, trust and explainability issues, unfavorable end-user perceptions and uncertain economic value would require a combination approach.
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.