Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Интерпретация моделей «чёрного ящика»: обзор объяснимого искусственного интеллекта
2023-08-24
SCID: 54.1/j9xq649n
Discuss with AI
Black-box modelsDeep learningExplainable artificial intelligenceMachine learningModel interpretability
Figures from the paper
Abstract (AI)
Abstract Recent years have seen a tremendous growth in Artificial Intelligence (AI)-based methodological development in a broad range of domains. In this rapidly evolving field, large number of methods are being reported using machine learning (ML) and Deep Learning (DL) models. Majority of these models are inherently complex and lacks explanations of the decision making process causing these models to be termed as 'Black-Box'. One of the major bottlenecks to adopt such models in mission-critical application domains, such as banking, e-commerce, healthcare, and public services and safety, is the difficulty in interpreting them. Due to the rapid proleferation of these AI models, explaining their learning and decision making process are getting harder which require transparency and easy predictability. Aiming to collate the current state-of-the-art in interpreting the black-box models, this study provides a comprehensive analysis of the explainable AI (XAI) models. To reduce false negative and false positive outcomes of these back-box models, finding flaws in them is still difficult and inefficient. In this paper, the development of XAI is reviewed meticulously through careful selection and analysis of the current state-of-the-art of XAI research. It also provides a comprehensive and in-depth evaluation of the XAI frameworks and their efficacy to serve as a starting point of XAI for applied and theoretical researchers. Towards the end, it highlights emerging and critical issues pertaining to XAI research to showcase major, model-specific trends for better explanation, enhanced transparency, and improved prediction accuracy.
Key Findings
1
Black-box ML and deep learning models lack transparent decision-making explanations, limiting their adoption in mission-critical domains.
2
Emerging XAI research trends emphasize model-specific explanations, greater transparency, and improved prediction accuracy.
3
The review comprehensively analyzes state-of-the-art explainable AI methods and frameworks for interpreting complex AI models.
4
The study evaluates XAI frameworks and their efficacy, providing a reference point for applied and theoretical researchers.
5
XAI can help identify model flaws and reduce false-negative and false-positive outcomes, although detecting such issues remains difficult and inefficient.
Research Object
Black-box machine learning and deep learning models (AI models)
Research Subject
explainability, interpretability, transparency, and predictive efficacy of these models, including methods for explaining their learning and decision-making processes
Publication Details
Publication Date
2023-08-24
Journal
Publisher
ISSN
Cited by
2921
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai17
ImageNet classification with deep convolutional neural networks2017
A Unified Approach to Interpreting Model Predictions2017
Greedy function approximation: A gradient boosting machine.2001
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
Distilling the Knowledge in a Neural Network2015
Intriguing properties of neural networks2013
Learning Deep Features for Discriminative Localization2016
Towards A Rigorous Science of Interpretable Machine Learning2017
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)2018
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI2020
Explainability for artificial intelligence in healthcare: a multidisciplinary perspective2020
Interpretable machine learning: Fundamental principles and 10 grand challenges2022
Designing Theory-Driven User-Centric Explainable AI2019
A Survey of Methods for Explaining Black Box Models2018
Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities2022
"What is relevant in a text document?": An interpretable machine learning approach2017
A Survey on Big Data Analytics: Challenges, Open Research Issues and Tools2016
Cited by8
Explainable artificial intelligence (XAI) in finance: a systematic literature review2024
Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer’s disease detection2024
THE ROLE OF AI IN MARKETING PERSONALIZATION: A THEORETICAL EXPLORATION OF CONSUMER ENGAGEMENT STRATEGIES2024
Agentic AI Frameworks in SMMEs: A Systematic Literature Review of Ecosystemic Interconnected Agents2025
Digital Twin Cognition: AI-Biomarker Integration in Biomimetic Neuropsychology2025
Exploring Agentic AI in Healthcare: A Study on Its Working Mechanism2026
Advancing chemical engineering technology with artificial intelligence2025
Artificial intelligence and digital innovations in precision aquaculture: Advancements, applications, and future directions2026