Explainable AI: A Review of Machine Learning Interpretability Methods
Explore this paper's citation graph
Summary
This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.
- Type
- review
- Published
- 2020-12-25
- Cited by
- 2,765
- References
- 167
- Access
- Open access
- OpenAlex
- https://openalex.org/W3116286104
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:229722844
Keywords
Interpretability, Artificial intelligence, Computer science, Machine learning, Ambiguity
References
- Global Sensitivity Analysis: The Primer
- Classification and Regression by randomForest
- Factorial sampling plans for preliminary computational experiments
- Intriguing properties of neural networks
- Greedy function approximation: A gradient boosting machine.
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
- Understanding Neural Networks Through Deep Visualization
- Machine learning: Trends, perspectives, and prospects
- Saliency detection by multi-context deep learning
- Global sensitivity measures from given data
- Decision Theory for Discrimination-Aware Classification
- A new uncertainty importance measure
- Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
- Certifying and Removing Disparate Impact
- Making best use of model evaluations to compute sensitivity indices
- Derivative based global sensitivity measures and their link with global sensitivity indices
- Random balance designs for the estimation of first order global sensitivity indices
- Accurate intelligible models with pairwise interactions
- Generalized Linear Models
- Bias correction for the estimation of sensitivity indices based on random balance designs
Cited by
- Standing on the shoulders of giants
- Generalizing Correspondence Analysis for Applications in Machine Learning
- Explainable empirical risk minimization
- Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximization
- Anthropogenic influence on extreme precipitation over global land areas seen in multiple observational datasets
- An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification
- Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice
- A Review on Explainability in Multimodal Deep Neural Nets
- Explainable Artificial Intelligence for Human Decision-Support System in Medical Domain
- Interpretable machine learning for genomics
- Shall I Work with Them? A Knowledge Graph-Based Approach for Predicting Future Research Collaborations
- A pilot study: quantify lung volume and emphysema extent directly from 2-D scout images.
- Sentiment Analysis for Fake News Detection
- Keep CALM and Improve Visual Feature Attribution
- Similarity network fusion for the integration of multi-omics and microbiomes in respiratory disease
- Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review
- Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review
- Explainable Diabetic Retinopathy Detection and Retinal Image Generation
- Recent Studies of XAI - Review
- A Novel Approach for Data Analysis using Explainable AI
Related papers
- Demystifying Black Box Models with Neural Networks for Accuracy and Interpretability of Supervised Learning
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- Interpretability Vs Explainability: The Black Box of Machine Learning
- A Theory of Diagnostic Interpretation in Supervised Classification
- Innovative approaches to addressing the tradeoff between interpretability and accuracy in ship fuel consumption prediction
- Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Model
- Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
- Interpretable Approaches to Detect Bias in Black-Box Models
- Explaining Explainability: Interpretable machine learning for the behavioral sciences