Towards Explainable Artificial Intelligence

Abstract

In recent years, machine learning (ML) has become a key enabling technology for the sciences and industry. Especially through improvements in methodology, the availability of large databases and increased computational power, today's ML algorithms are able to achieve excellent performance (at times even exceeding the human level) on an increasing number of complex tasks. Deep learning models are at the forefront of this development. However, due to their nested non-linear structure, these powerful models have been generally considered "black boxes", not providing any information about what exactly makes them arrive at their predictions. Since in many applications, e.g., in the medical domain, such lack of transparency may be not acceptable, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This introductory paper presents recent developments and applications in this field and makes a plea for a wider use of explainable learning algorithms in practice.

19 pages

References in corpus (35)

• A Unified Approach to Interpreting Model Predictions
• WaveNet: A Generative Model for Raw Audio
• Towards A Rigorous Science of Interpretable Machine Learning
• Axiomatic Attribution for Deep Networks
• Methods for Interpreting and Understanding Deep Neural Networks
• Learning Important Features Through Propagating Activation Differences
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Understanding Neural Networks Through Deep Visualization
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Understanding Black-box Predictions via Influence Functions
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Interpretable Explanations of Black Boxes by Meaningful Perturbation
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
• SmoothGrad: removing noise by adding noise
• How to Explain Individual Classification Decisions
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Learning both Weights and Connections for Efficient Neural Networks
• Robust Physical-World Attacks on Deep Learning Models
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
• Understanding Neural Networks through Representation Erasure
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• Learning how to explain neural networks: PatternNet and PatternAttribution
• "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
• Explaining the Unique Nature of Individual Gait Patterns with Deep Learning
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• An Evaluation of the Human-Interpretability of Explanation
• From Clustering to Cluster Explanations via Neural Networks
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• Explaining and Interpreting LSTMs
• Interpreting Black Box Predictions using Fisher Kernels
• Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profiles
• Enhanced Rotational Invariant Convolutional Neural Network for Supernovae Detection

Cited by in corpus (43)

• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
• Transformer-CNN: Fast and Reliable tool for QSAR
• Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
• Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance with Machine Learning
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Levels of explainable artificial intelligence for human-aligned conversational explanations
• Explainable Artificial Intelligence: a Systematic Review
• A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical Applications
• XAIR: A Framework of Explainable AI in Augmented Reality
• Deep Learning in Business Analytics: A Clash of Expectations and Reality
• Two Decades of Bengali Handwritten Digit Recognition: A Survey
• A Survey on Neural Network Interpretability
• Impact of the characteristics of quantum chemical databases on machine learning predictions of tautomerization energies
• Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning -- A Residual Physics Approach
• Neural network fragile watermarking with no model performance degradation
• This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks
• Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation
• A Taxonomy of Explainable Bayesian Networks
• Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems
• Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond
• Crowdsourcing Impacts: Exploring the Utility of Crowds for Anticipating Societal Impacts of Algorithmic Decision Making
• Subtyping patients with chronic disease using longitudinal BMI patterns
• Efficient Explanations for Knowledge Compilation Languages
• Delivering Inflated Explanations
• On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations
• Human-Centered Evaluation of XAI Methods
• A Conceptual Framework for Establishing Trust in Real World Intelligent Systems
• Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities
• Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models
• This Reads Like That: Deep Learning for Interpretable Natural Language Processing
• What should AI see? Using the Public's Opinion to Determine the Perception of an AI
• Explainable AI for Engineering Design: A Unified Approach of Systems Engineering and Component- Based Deep Learning Demonstrated by Energy- Efficient Building Design
• Extractive Text Summarization Using Generalized Additive Models with Interactions for Sentence Selection
• Integrating measures of replicability into scholarly search: Challenges and opportunities
• Generalizing Logic-based Explanations for Machine Learning Classifiers via Optimization
• DRILL-- Deep Reinforcement Learning for Refinement Operators in $\mathcal{A}\mathcal{LC}$
• Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
• M-ar-K-Fast Independent Component Analysis
• A Series of Unfortunate Counterfactual Events: the Role of Time in Counterfactual Explanations
• A2I Transformer: Permutation-equivariant attention network for pairwise and many-body interactions with minimal featurization
• Streamlining models with explanations in the learning loop