Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Explore this paper's citation graph
Summary
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.
- Type
- article
- Published
- 2018-09-17
- Cited by
- 5,338
- References
- 175
- Access
- Open access
- OpenAlex
- https://openalex.org/W2891503716
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52965836
Keywords
Transparency (behavior), Sine qua non, Computer science, Black box, Field (mathematics)
References
- Deep Learning, Dark Knowledge, and Dark Matter
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- The Truth is in There : Rule Extraction from Opaque Models Using Genetic Programming
- Falling Rule Lists
- An Explainable Artificial Intelligence System for Small-unit Tactical Behavior
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
- Distilling the Knowledge in a Neural Network
- Understanding deep image representations by inverting them
- Design and Evaluation of Explainable BDI Agents
- Guidelines for snowballing in systematic literature studies and a replication in software engineering
- Too much, too little, or just right? Ways explanations impact end users' mental models
- Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
- An ontology-based interface for machine learning
- An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models
- Are explanations always important?: a study of deployed, low-cost intelligent interactive systems
- Overview of: “Statistical Procedures for Forecasting Criminal Behavior: A Comparative Assessment”
- Trading Interpretability for Accuracy: Oblique Treed Sparse Additive Models
- The CAD-MDD: A Computerized Adaptive Diagnostic Screening Tool for Depression
- Survey and critique of techniques for extracting rules from trained artificial neural networks
- Quantitative Measurements of model interpretability for the analysis of spectral data
Cited by
- Intelligent Data Engineering and Automated Learning – IDEAL 2020: 21st International Conference, Guimaraes, Portugal, November 4–6, 2020, Proceedings, Part II
- Productivity, Portability, Performance: Data-Centric Python
- A View on Vulnerabilites: The Security Challenges of XAI (Academic Track)
- Logic Negation with Spiking Neural P Systems
- The importance of interpretability and visualization in machine learning for applications in medicine and health care
- Physics Enhanced Artificial Intelligence
- Shared Mental Models as a Way of Managing Transparency in Complex Human-Autonomy Teaming
- GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks
- Gastroenterology Meets Machine Learning: Status Quo and Quo Vadis
- Personalized explanation in machine learning
- Assuring the Machine Learning Lifecycle
- Explainable Agents and Robots: Results from a Systematic Literature Review
- Interpretable Deep Neural Networks for Patient Mortality Prediction: A Consensus-based Approach
- Explainable automatic target recognition (XATR)
- Explainable Machine Learning for Scientific Insights and Discoveries
- The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning
- Enabling Dynamic Network Access Control with Anomaly-based IDS and SDN
- PalmNet: Gabor-PCA Convolutional Networks for Touchless Palmprint Recognition
- An Application of Combinatorial Methods for Explainability in Artificial Intelligence and Machine Learning (Draft)
- Towards a Generic Framework for Black-box Explanation Methods (Extended Version)
Related papers
- The emergence of a "flexible" conditio sine qua non test to factual causation?Lee v Minister of Correctional Services 2013 (2) SA 144 (CC) : cases
- Ethics of economic justice and inclusion: A sine qua non for psychologists.
- World‐Wide Idea Registration in a Global Idea Bank Is a sine qua non to Protect Present Intellectual Property Ideas for Posterity
- Indigenous knowledge systems a sine-qua-non in the conception and maintenance of sustainable development : foreword
- ТЕОРІЯ АКТИВІВ І КАПІТАЛУ ЗОВНІШНЬОГО СЕРЕДОВИЩА ПІДПРИЄМСТВА: CONDITIO SINE QUA NON // Theory of assets and equity of external environment of a company: conditio sine qua non