Methods for Interpreting and Understanding Deep Neural Networks

Abstract

This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed techniques of interpretation, along with theory, tricks and recommendations, to make most efficient use of these techniques on real data. It also discusses a number of practical applications.

14 pages, 10 figures

References in corpus (17)

• Striving for Simplicity: The All Convolutional Net
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• On the Number of Linear Regions of Deep Neural Networks
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• How to Explain Individual Classification Decisions
• Finding Density Functionals with Machine Learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Self-Normalizing Neural Networks
• Practical recommendations for gradient-based training of deep architectures
• "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• Feature Importance Measure for Non-linear Learning Algorithms
• Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers

Cited by in corpus (318)

• EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces
• A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
• SchNet - a deep learning architecture for molecules and materials
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• A trans-disciplinary review of deep learning research for water resources scientists
• Explainable Machine Learning for Scientific Insights and Discoveries
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• A Survey on the Explainability of Supervised Machine Learning
• Machine learning for molecular simulation
• A Unifying Review of Deep and Shallow Anomaly Detection
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
• Explaining Explanations in AI
• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Towards Explainable Artificial Intelligence
• This Looks Like That: Deep Learning for Interpretable Image Recognition
• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• Towards Robust Interpretability with Self-Explaining Neural Networks
• On scientific understanding with artificial intelligence
• Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
• Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• SNAS: Stochastic Neural Architecture Search
• "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
• Explaining the Unique Nature of Individual Gait Patterns with Deep Learning
• Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
• Challenges of Real-World Reinforcement Learning
• Weak SINDy For Partial Differential Equations
• Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Machine-Learning-Based Diagnostics of EEG Pathology
• Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• Detecting and interpreting myocardial infarction using fully convolutional neural networks
• Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI
• From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
• Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
• Bridging observation, theory and numerical simulation of the ocean using Machine Learning
• Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping
• Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions
• Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020-2022
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• On the Explainability of Natural Language Processing Deep Models
• DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
• Toward Explainable AI for Regression Models
• From Clustering to Cluster Explanations via Neural Networks
• XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data
• Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
• RUDDER: Return Decomposition for Delayed Rewards
• Explainable Deep One-Class Classification
• TSViz: Demystification of Deep Learning Models for Time-Series Analysis
• Exploring Interpretable LSTM Neural Networks over Multi-Variable Data
• Programmatically Interpretable Reinforcement Learning
• Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer's Disease
• Explainable Artificial Intelligence: a Systematic Review
• Machine Learning for Condensed Matter Physics
• From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology
• Interpretable deep learning for guided structure-property explorations in photovoltaics
• On the Explanation of Machine Learning Predictions in Clinical Gait Analysis
• Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
• Explaining and Interpreting LSTMs
• Interpreting and Stabilizing Machine-learning Parametrizations of Convection
• Building and Interpreting Deep Similarity Models
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• On the (In)fidelity and Sensitivity for Explanations
• Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
• Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
• Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps
• Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment
• On Information Plane Analyses of Neural Network Classifiers -- A Review
• Interpreting recurrent neural networks behaviour via excitable network attractors
• Concise Fuzzy System Modeling Integrating Soft Subspace Clustering and Sparse Learning
• On Tackling Explanation Redundancy in Decision Trees
• Understanding Unequal Gender Classification Accuracy from Face Images
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Recurrent neural network-based volumetric fluorescence microscopy
• Toward Accurate Interpretable Predictions of Materials Properties within Transformer Language Models
• An XAI framework for robust and transparent data-driven wind turbine power curve models
• Getting a CLUE: A Method for Explaining Uncertainty Estimates
• Defining Explainable AI for Requirements Analysis
• Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
• Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability
• Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
• Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
• Towards Explainable Neural-Symbolic Visual Reasoning
• Understanding and Comparing Deep Neural Networks for Age and Gender Classification
• Considerations When Learning Additive Explanations for Black-Box Models
• AI for the prediction of early stages of Alzheimer's disease from neuroimaging biomarkers -- A narrative review of a growing field
• The Clever Hans Effect in Unsupervised Learning
• A Survey on Neural Network Interpretability
• Intrapapillary Capillary Loop Classification in Magnification Endoscopy: Open Dataset and Baseline Methodology
• Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models
• Towards falsifiable interpretability research
• PSF--NET: A Non-parametric Point Spread Function Model for Ground Based Optical Telescopes
• Applications of Generative AI in Healthcare: algorithmic, ethical, legal and societal considerations
• Deep Residual Autoencoder for quality independent JPEG restoration
• Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks
• iNNvestigate neural networks!
• IcoRating: A Deep-Learning System for Scam ICO Identification
• Can counterfactual explanations of AI systems' predictions skew lay users' causal intuitions about the world? If so, can we correct for that?
• Q-value Path Decomposition for Deep Multiagent Reinforcement Learning
• NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Polarization Simulation
• Gaussian Process Latent Class Choice Models
• An explainable deep vision system for animal classification and detection in trail-camera images with automatic post-deployment retraining
• Explainable artificial intelligence model to predict acute critical illness from electronic health records
• Bias in Data-driven AI Systems -- An Introductory Survey
• Insights Into the Inner Workings of Transformer Models for Protein Function Prediction
• Model extraction from counterfactual explanations
• Foreword to the Focus Issue on Machine Learning in Astronomy and Astrophysics
• Stochastic Mutual Information Gradient Estimation for Dimensionality Reduction Networks
• Model Agnostic Multilevel Explanations
• Structural Compression of Convolutional Neural Networks
• An Information-Theoretic Approach to Personalized Explainable Machine Learning
• Fairwashing: the risk of rationalization
• Perceptron Theory Can Predict the Accuracy of Neural Networks
• How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
• TIP: Typifying the Interpretability of Procedures
• A Comparative Study of Machine Learning Models for Predicting the State of Reactive Mixing
• Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems
• Can Requirements Engineering Support Explainable Artificial Intelligence? Towards a User-Centric Approach for Explainability Requirements
• Improving Simple Models with Confidence Profiles
• Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
• ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation
• Explaining Bayesian Neural Networks
• Interpretable Approximation of High-Dimensional Data
• Domain Knowledge Aided Explainable Artificial Intelligence for Intrusion Detection and Response
• A Rate-Distortion Framework for Explaining Neural Network Decisions
• Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks
• Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoring
• Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models
• Convolutional Recurrent Neural Networks for Glucose Prediction
• Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond
• Feature Visualization within an Automated Design Assessment leveraging Explainable Artificial Intelligence Methods
• Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Tools
• Deep Representation Learning for Social Network Analysis
• Robustifying Models Against Adversarial Attacks by Langevin Dynamics
• Personalized explanation in machine learning: A conceptualization
• Interpretable Deep Convolutional Neural Networks via Meta-learning
• Revisiting Sanity Checks for Saliency Maps
• The Convergence of Machine Learning and Communications
• Progressive Disclosure: Designing for Effective Transparency
• Emergence of Network Motifs in Deep Neural Networks
• Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
• On Relating 'Why?' and 'Why Not?' Explanations
• Applying saliency-map analysis in searches for pulsars and fast radio bursts
• Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
• Improving the Interpretability of Deep Neural Networks with Knowledge Distillation
• PredDiff: Explanations and Interactions from Conditional Expectations
• Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition
• CDT: Cascading Decision Trees for Explainable Reinforcement Learning
• Are Adversarial Perturbations a Showstopper for ML-Based CAD? A Case Study on CNN-Based Lithographic Hotspot Detection
• Sparse Oblique Decision Trees: A Tool to Understand and Manipulate Neural Net Features
• Model Explainability in Deep Learning Based Natural Language Processing
• Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition
• Capsule Networks for Protein Structure Classification and Prediction
• Class Feature Pyramids for Video Explanation
• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
• Teaching Meaningful Explanations
• Achieving Generalizable Robustness of Deep Neural Networks by Stability Training
• Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI
• Saliency-driven Word Alignment Interpretation for Neural Machine Translation
• Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
• Regularizing Reasons for Outfit Evaluation with Gradient Penalty
• Deep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective
• Regional Tree Regularization for Interpretability in Black Box Models
• Probing Criticality in Quantum Spin Chains with Neural Networks
• Hierarchical Matrix Factorization for Interpretable Collaborative Filtering
• ECQ${}^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
• Why an Android App is Classified as Malware? Towards Malware Classification Interpretation
• Exploring text datasets by visualizing relevant words
• Adversarial Attacks and Defenses: An Interpretation Perspective
• Learning Fair Rule Lists
• Noise reduction on single-shot images using an autoencoder
• Debugging Tests for Model Explanations
• Achievements and Challenges in Explaining Deep Learning based Computer-Aided Diagnosis Systems
• Identifying Dominant Industrial Sectors in Market States of the S&P 500 Financial Data
• Deep Learning in Information Security
• Analysis of Invariance and Robustness via Invertibility of ReLU-Networks
• Efficient Search for Diverse Coherent Explanations
• Dual Recurrent Attention Units for Visual Question Answering
• GAN-based Generation and Automatic Selection of Explanations for Neural Networks
• Neural Architecture Search by Estimation of Network Structure Distributions
• Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks
• Complementary reinforcement learning towards explainable agents
• Deep Feature Factorization For Concept Discovery
• A Survey on the Robustness of Feature Importance and Counterfactual Explanations
• Causal Analysis of Agent Behavior for AI Safety
• Attribution Preservation in Network Compression for Reliable Network Interpretation
• Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models
• Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task
• DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models
• Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
• A Simple Saliency Method That Passes the Sanity Checks
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning
• Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
• A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks
• Efficient Explanations With Relevant Sets
• Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency
• Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation
• A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language
• Satellite galaxies' drag on field stars in the Milky Way
• Ranking Micro-Influencers: a Novel Multi-Task Learning and Interpretable Framework
• Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors
• Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease
• Interpreting Interpretations: Organizing Attribution Methods by Criteria
• Learning Credible Deep Neural Networks with Rationale Regularization
• Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
• Evaluation, Tuning and Interpretation of Neural Networks for Meteorological Applications
• A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-Learning
• A Factored Generalized Additive Model for Clinical Decision Support in the Operating Room
• Ensemble Transfer Learning of Elastography and B-mode Breast Ultrasound Images
• Explainable Empirical Risk Minimization
• Towards Interpretable Deep Learning Models for Knowledge Tracing
• Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
• On Efficiently Explaining Graph-Based Classifiers
• Towards Robust Explanations for Deep Neural Networks
• Fabrication uncertainty guided design optimization of a photonic crystal cavity by using Gaussian processes
• The Skincare project, an interactive deep learning system for differential diagnosis of malignant skin lesions. Technical Report
• Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling
• The Impact of Feature Representation on the Accuracy of Photonic Neural Networks
• EMAP: Explanation by Minimal Adversarial Perturbation
• Shapley Interpretation and Activation in Neural Networks
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• Learning from learning machines: a new generation of AI technology to meet the needs of science
• Deriving Equivalent Symbol-Based Decision Models from Feedforward Neural Networks
• Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI
• Discovering topics in text datasets by visualizing relevant words
• Scene Text Recognition Models Explainability Using Local Features
• A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution
• An XAI Approach to Deep Learning Models in the Detection of DCIS
• Location, location, location: Satellite image-based real-estate appraisal
• Progress in deep Markov State Modeling: Coarse graining and experimental data restraints
• Paying Attention to Attention: Highlighting Influential Samples in Sequential Analysis
• Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
• Hydroelectric Generation Forecasting with Long Short Term Memory (LSTM) Based Deep Learning Model for Turkey
• Explainable Recommender Systems via Resolving Learning Representations
• Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
• Challenges for Predictive Modeling with Neural Network Techniques using Error-Prone Dietary Intake Data
• Fast gradient-free activation maximization for neurons in spiking neural networks
• An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness
• Neural Machine Translation: A Review and Survey
• Computing Optimal Decision Sets with SAT
• Random Polytope Descriptors
• Interpretable Time-series Classification on Few-shot Samples
• Newton-Puiseux Analysis for Interpretability and Calibration of Complex-Valued Neural Networks
• TIME: A Transparent, Interpretable, Model-Adaptive and Explainable Neural Network for Dynamic Physical Processes
• Visualizing Image Content to Explain Novel Image Discovery
• Explaining Neural Network Predictions for Functional Data Using Principal Component Analysis and Feature Importance
• SMILES-X: autonomous molecular compounds characterization for small datasets without descriptors
• Computer Vision and Deep Learning for Fish Classification in Underwater Habitats: A Survey
• Reachability Analysis of Convolutional Neural Networks
• Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
• A general approach to compute the relevance of middle-level input features
• Integrating Intrinsic and Extrinsic Explainability: The Relevance of Understanding Neural Networks for Human-Robot Interaction
• An Analytic Layer-wise Deep Learning Framework with Applications to Robotics
• A General Taylor Framework for Unifying and Revisiting Attribution Methods
• Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions
• An AI-Augmented Lesion Detection Framework For Liver Metastases With Model Interpretability
• Designing Visual Explanations and Learner Controls to Engage Adolescents in AI-Supported Exercise Selection
• Feedback System Neural Networks for Inferring Causality in Directed Cyclic Graphs
• Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-making
• On Explaining Random Forests with SAT
• On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
• "I had a solid theory before but it's falling apart": Polarizing Effects of Algorithmic Transparency
• Deep Learning Based Decision Support for Medicine -- A Case Study on Skin Cancer Diagnosis
• Explaining the Road Not Taken
• Inference of cell dynamics on perturbation data using adjoint sensitivity
• Assessing the Reliability of Visual Explanations of Deep Models with Adversarial Perturbations
• Understanding Patch-Based Learning by Explaining Predictions
• PLANS: Robust Program Learning from Neurally Inferred Specifications
• Understanding Recurrent Neural State Using Memory Signatures
• Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork
• Position Paper: Towards Transparent Machine Learning
• Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization
• Coherence of Working Memory Study Between Deep Neural Network and Neurophysiology
• Self-explaining variational posterior distributions for Gaussian Process models
• A Framework to Learn with Interpretation
• Focused LRP: Explainable AI for Face Morphing Attack Detection
• A User-Centred Framework for Explainable Artificial Intelligence in Human-Robot Interaction
• A crossover code for high-dimensional composition
• IFBiD: Inference-Free Bias Detection
• Deep Relevance Regularization: Interpretable and Robust Tumor Typing of Imaging Mass Spectrometry Data
• T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP
• Explaining Classes through Word Attribution
• Distilling neural networks into skipgram-level decision lists
• Explaining Anomalies in Groups with Characterizing Subspace Rules
• Explaining a prediction in some nonlinear models
• An Interpretable Neural Network for Parameter Inference
• Regression Concept Vectors for Bidirectional Explanations in Histopathology
• Explainability by Design: Structured Kolmogorov-Arnold Networks over Probabilistic Attributes for Speech Deepfake Source Tracing
• Data-Driven Continuum Dynamics via Transport-Teleport Duality
• On the interpretability of neural network decoders
• Clusters in Explanation Space: Inferring disease subtypes from model explanations
• Pull-back Geometry of Persistent Homology Encodings
• A Neural-Symbolic Framework for Mental Simulation
• Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks
• Cosmic velocity, density and halo mass function: Insights from deep learning
• Langevin Cooling for Domain Translation
• ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
• Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks
• Assessing The Importance Of Colours For CNNs In Object Recognition
• Convolutional Neural Networks from Image Markers
• On Predictive Explanation of Data Anomalies
• Evaluating Attribution Methods using White-Box LSTMs
• Investigating ADR mechanisms with knowledge graph mining and explainable AI
• Logic Constraints to Feature Importances
• An Overview of Computational Approaches for Interpretation Analysis
• Get It Scored Using AutoSAS -- An Automated System for Scoring Short Answers