Toward Human-Understandable, Explainable AI

2018/09/01 by Hani Hagras · 29 citations
Computer Science · #Explainable Artificial Intelligence (XAI) #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications

paper · doi:10.1109/mc.2018.3620965

Abstract

Recent increases in computing power, coupled with rapid growth in the availability and quantity of data have rekindled our interest in the theory and applications of artificial intelligence (AI). However, for AI to be confidently rolled out by industries and governments, users want greater transparency through explainable AI (XAI) systems. The author introduces XAI concepts, and gives an overview of areas in need of further exploration—such as type-2 fuzzy logic systems—to ensure such systems can be fully understood and analyzed by the lay user.

Citations

• European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”

Cited by

• Explainable Empirical Risk Minimization
• Explainability Methods for Hardware Trojan Detection: A Systematic Comparison
• Artificial Intelligence in the Global South (AI4D): Potential and Risks
• Artificial intelligence in dentistry—A review
• Explainable Artificial Intelligence (XAI): An Engineering Perspective
• A Topological Framework for Deep Learning
• A Self-Organizing Fuzzy Logic Classifier for Benchmarking Robot-Aided Blasting of Ship Hulls. [europepmc]
• A bird's-eye view of deep learning in bioimage analysis. [europepmc]
• An IOHMM-Based Framework to Investigate Drift in Effectiveness of IoT-Based Systems. [europepmc]
• In Search of Trustworthy and Transparent Intelligent Systems With Human-Like Cognitive and Reasoning Capabilities. [europepmc]
• Explainable artificial intelligence based analysis for interpreting infant fNIRS data in developmental cognitive neuroscience. [europepmc]
• On the Commoditization of Artificial Intelligence. [europepmc]
• An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila. [europepmc]
• Augmenting Social Science Research with Multimodal Data Collection: The EZ-MMLA Toolkit. [europepmc]
• Affective Response Categories-Toward Personalized Reactions in Affect-Adaptive Tutoring Systems. [europepmc]
• Using Explainable Artificial Intelligence to Discover Interactions in an Ecological Model for Obesity. [europepmc]
• Toward explainable AI-empowered cognitive health assessment. [europepmc]
• Predicting and understanding human action decisions during skillful joint-action using supervised machine learning and explainable-AI. [europepmc]
• The role of explainable Artificial Intelligence in high-stakes decision-making systems: a systematic review. [europepmc]
• The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP. [europepmc]
• Humans and cyber-physical systems as teammates? Characteristics and applicability of the human-machine-teaming concept in intelligent manufacturing. [europepmc]
• Using fNIRS to Identify Transparency- and Reliability-Sensitive Markers of Trust Across Multiple Timescales in Collaborative Human-Human-Agent Triads. [europepmc]
• Interpretable predictions of chaotic dynamical systems using dynamical system deep learning. [europepmc]
• Corn leaf disease: insightful diagnosis using VGG16 empowered by explainable AI. [europepmc]
• Artificial intelligence in dentistry-A review. [europepmc]
• [Robotics in Information Systems]. [europepmc]
• Deriving equivalent symbol-based decision models from feedforward neural networks. [europepmc]
• Advancing occupational exposure models: insights from a case study [europepmc]
• Virtual-reality-based digital twin of office spaces with social distance measurement feature [europepmc]

Related

• Reviewing the Need for Explainable Artificial Intelligence (xAI)
• Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities
• Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities
• Explainable AI: current status and future directions
• XAI-P-T: A Brief Review of Explainable Artificial Intelligence from Practice to Theory