The paper connects neural networks to Mahalanobis distance for interpretability.
problem Lack of interpretability in neural networks.
method Establishes a connection between neural network linear layers and Mahalanobis distance.
result Provides a foundation for more interpretable neural network models.
Neural networks improve geoscience by enabling interpretable decision pathways.
problem Lack of methods to interpret neural networks' learning and decision-making.
method Backwards optimization and layerwise relevance propagation.
result Interpretation techniques reveal meaningful connections in geoscientific data.
Interpretable neural networks improve economic research by balancing accuracy and transparency.
problem Lack of interpretability in neural networks hinders their use in economic research.
method Proposes interpretable neural network models that balance prediction accuracy and interpretability.
result Achieved 94.5% accuracy in predicting employment status using high-dimensional data.
Adversarial manipulation fools neural network interpretations.
problem Ensuring interpretation methods are robust to model manipulations.
method Integrating manipulation into fine-tuning objective function.
result State-of-the-art interpreters can be fooled with minimal accuracy loss.
Neural networks explained through geometric projections.
problem Understanding the geometric and mathematical underpinnings of neural networks.
method Exploiting connections between integration, Radon transforms, and neural networks.
result Distribution of neural network outputs can be interpreted as nonlinear projections along hypersurfaces.
Survey on understanding neural networks for medical applications.
problem Black-box nature of deep neural networks hinders their use in critical applications.
method Comprehensive review of interpretability studies in neural networks.
result Interpretability research is crucial for the acceptance of neural networks in medical diagnosis.
Pruning neural networks reduces parameters without sacrificing interpretability.
problem Reducing unnecessary structure in neural networks to improve efficiency.
method Examined the effect of pruning on the number of hidden units learning disentangled representations.
result Pruning does not harm interpretability until a significant portion of parameters are removed.
Proposes NLRL for enhancing neural networks' interpretability.
problem Deep neural networks lack interpretability for humans.
method Introduces neural logic rule layers (NLRL) to represent arbitrary logic rules.
result NLRL-enhanced neural networks can learn complex logic and arithmetic.
A new Shapley value approach for neural networks interpretable and stable.
problem Neural networks' interpretability and training stability issues.
method Shapley value approximation for ReLU activation, globally continuous Shapley gradient, Shapley Activation function.
result SA consistently outperforms ReLU in training convergence, accuracy, and stability.
New method improves neural network interpretability against adversarial attacks.
problem Adversarial attacks can hide from neural network interpretability methods.
method Develops an interpretability-aware defensive scheme promoting robust interpretation.
result Achieves both robust classification and robust interpretation.
Study enhances neural network interpretability through statistical methods.
problem Complexity and interpretability challenges in neural networks.
method Theoretical framework, statistical tests, dimensionality reduction algorithms.
result Developed bootstrapping technique and statistical tests for ANN performance.
AWD distills neural network info into interpretable wavelets.
problem Imbalanced interpretability and efficiency in deep learning models.
method Adaptive wavelet distillation (AWD) penalizes neural network attributions in wavelet domain.
result AWD yields a concise, efficient, and interpretable model.
The paper proposes a consensus algorithm to improve deep neural network interpretability and accuracy in mortality prediction.
problem The black-box nature and overgeneralization of deep neural networks in healthcare applications.
method An (n, k) consensus algorithm that is insensitive to adversarial examples and can reliably reject out-of-distribution samples. result The consensus algorithm improves both prediction accuracy and interpretability of deep neural network models in mortality prediction.
Hides the complexity of neural networks, making them more transparent.
problem Lack of transparency in Neural Networks hinders their adoption.
method Proposes Hide-and-Seek (HnS) framework for training interpretable neural networks.
result Interpretable neural networks can be trained without sacrificing predictive power.
New method interprets deep neural networks for better recommendation system understanding.
problem Making deep neural networks explainable for better user trust and understanding.
method Proposes a novel formulation of interpretable deep neural networks using masked weights and hidden features.
result Demonstrates models achieving close predictive performance with informative attributions.
Paper proposes a method to interpret deep neural networks using attention mechanisms.
problem Interpreting deep neural network models to understand their performance.
method Proposes a novel method using attention mechanisms to analyze neural network models.
result Improved attention based method shows better classifier interpretation.
XDeep interprets deep neural networks for practitioners and researchers.
problem Understanding and interpreting deep neural networks.
method Post-hoc interpretation algorithms integrated into XDeep.
result XDeep provides local and global explanations for deep models.
Proposes a copula-based method to interpret neural networks.
problem Neural networks lack interpretability due to ambiguity in decision-making.
method Uses pair copula correlation coefficients to reveal feature importance and decision paths.
result Consistent results with Random Forest's feature importance values.
Improves interpretability of recurrent neural networks through probabilistic abstraction.
problem Limited interpretability of neural networks, especially recurrent ones.
method Proposes a probabilistic approach to extract automata from recurrent neural networks.
result Significantly improves accuracy and scalability of interpretability compared to existing methods.
Locally sparse neural networks improve interpretability for biomedical tabular data.
problem Overfitting and lack of interpretability in neural networks for tabular biomedical data.
method Locally sparse neural network with a gating network to select relevant features.
result The method outperforms state-of-the-art models in synthetic and real-world biomedical datasets.
Bayesian explanations are more resilient to adversarial attacks than deterministic ones.
problem Stability of saliency-based explanations under adversarial attacks in Neural Networks.
method Empirical and theoretical analysis of Bayesian vs deterministic Neural Networks.
result Bayesian explanations are more stable under adversarial perturbations and direct attacks.
Automated method finds meaningful directions in neural network activations.
problem Mixed selectivity in neurons makes interpretation challenging.
method Automated quantification of interpretability and discovery of meaningful directions.
result Meaningful directions in neural network activations are more interpretable than individual neurons.
New method creates universal perturbations to fool neural network interpretations.
problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).
Interprets neural network classifiers for categorical inputs.
problem Neural networks' interpretability in human-sensitive applications.
method Mapping to physical energy model, expansion of neural network layers.
result Each layer's contribution to classification can be analyzed.
Combines neural networks and logic circuits for interpretable, accurate, and cost-effective learning.
problem Lack of generalizability and interpretability in neural networks and high hardware cost in logic circuits.
method Trains a neural network, then translates it to random forests, and finally to AND-Inverter logic.
result The pipeline maintains greater accuracy and minimizes logic complexity.
YASENN interprets neural networks by partitioning activation sequences.
problem Interpreting complex neural network decisions.
method YASENN uses layer-wise gradient boosting decision trees to distill and partition neuron activation sequences.
result YASENN provides interpretable partitions of the input space, revealing neural network decision artifacts.
New definition of interpretability for deep neural networks.
problem Vague definition of interpretability for deep neural networks.
method Proposed a new definition of human predictability for interpretability of DNNs.
result Our definition will help to the research of interpretability of DNNs.
Workshop reviews techniques to understand neural NLP models.
problem Understanding the inner workings of neural networks in natural language processing.
method Systematic manipulation of inputs, decoding intermediate representations, modifying architectures, and testing on simplified languages.
result Various techniques can improve explainability of neural network models.
A method to interpret neural networks by isolating active subnetworks.
problem Interpreting the complex computations of deep neural networks.
method Switched linear projections to decompose network activity.
result Patterns in deactivated neurons are meaningful for network understanding.
AxNN improves model interpretability without sacrificing predictive power.
problem Black-box nature of machine learning models hinders interpretation and explanation.
method AxNN combines ensembles of generalized additive model networks and additive index models.
result AxNN achieves both good predictive performance and model interpretability.
Interpretable model for Granger causality using neural networks.
problem Inferring Granger causality in complex dynamical systems.
method Extension of self-explaining neural networks for multivariate Granger causality.
result Framework performs on par with baseline methods and better at inferring interaction signs.
Paper studies a universal logical operator for deep networks, improving interpretability.
problem Learning a universal logical operator for deep convolution networks without manual prescription.
method Exploration of different logical operators (AND, OR, XOR) and learning a universal one.
result Insightful observations lead to a novel logical interpretation of deep convolution networks.
Neural PID controllers improve control system performance and are more interpretable.
problem Lack of interpretability in neural PID controllers limits their use in control engineering.
method Extensive study using four benchmark systems with and without noise and disturbances, applying GDNN to PID controllers.
result Neural PID controllers outperform standard PID and model-based control in most tasks.
causalKANs provides interpretable treatment effect estimates using neural networks.
problem The opacity of deep neural networks limits their adoption in sensitive domains.
method Proposes causalKANs, a framework that transforms neural estimators into interpretable closed-form formulas.
result causalKANs performs on par with neural baselines in CATE error metrics and offers a favorable accuracy--interpretability trade-off.
Proposes ANOVA-TPNN for stable interpretation of complex functions.
problem Stability issues in estimating components of functional ANOVA models.
method Introduces ANOVA-TPNN based on tensor product basis expansion.
result ANOVA-TPNN provides stable estimation of components.
Equivariant neural networks use symmetry to interpret complex data.
problem Interpreting and understanding the behavior of equivariant neural networks.
method Decompose layers into simple representations and analyze nonlinear activation functions.
result Equivariant neural networks can be interpreted using a filtration generalizing Fourier series.
Dual neural network architecture improves accuracy and interpretability.
problem Improving neural network interpretability and accuracy.
method Stacked recurrent and feedforward layers, binary activation function.
result Binary activation leads to simpler, more interpretable models with higher accuracy.
nn2poly converts neural networks into interpretable polynomial models.
problem Interpreting complex neural networks.
method NN2Poly method for converting neural networks into polynomial models.
result Captures variable interactions and provides interpretable coefficients.
Paper learns an explainer to interpret CNN features without annotations.
problem Interpreting complex features in CNNs without labeled data.
method Unsupervised learning of an explainer to decompose and reconstruct feature maps.
result Explainer learns to reconstruct CNN features without losing information.
Study interprets deep learning for LHC jet tagging.
problem Understanding deep learning models in LHC jet tagging.
method Recursive neural networks, comparative study of jet tagging tasks.
result Interesting observations on the latent space of jet tagging models.
Simplifies PLNNs to interpretable models for better explainability.
problem Challenges in interpretability of PLNNs for high-stakes applications.
method Trained deep network simplification and algorithm for reducing flat networks.
result Improved interpretability of PLNNs without sacrificing performance.
New deep learning model improves image deblurring with interpretability.
problem Improving image deblurring performance with neural networks.
method Unrolling iterative algorithm to create a neural network architecture.
result Our deep network outperforms state-of-the-art methods in image deblurring.
MoreauGrad interprets neural nets robustly and sparsely.
problem Lack of robustness and sparsity in gradient-based interpretation methods.
method Moreau envelope for smooth and robust interpretation, combined with L1 regularization for sparsity.
result MoreauGrad provides a smooth, robust, and sparse explanation of neural nets.
PENN neural network estimates parameter distributions for econ models.
problem Lack of interpretability in deep neural networks for econ applications.
method Generative neural network architecture for Bayesian inference.
result PENN provides interpretable parameter estimates and visualizations.
neuralGAM package interprets neural networks by fitting them to feature contributions.
problem difficulty understanding neural network decisions
method Generalized Additive Neural Networks (GAM)
result interpretable Deep Learning model with accurate feature contributions
Proposes a neural network for contextual regression.
problem Improving model efficiency and interpretability in regression with contextual features.
method Simple contextual neural network (SCtxtNN) that separates context identification from context-specific regression.
result SCtxtNN achieves lower excess mean squared error and more stable performance than feed-forward neural networks.
Selective neural network improves credit risk prediction while maintaining interpretability.
problem Improving credit risk prediction accuracy while maintaining interpretability for financial regulators.
method Introducing a neural network with a selective option to distinguish between linear and non-linear datasets.
result For most datasets, logistic regression is sufficient and interpretable, while for specific data portions, a shallow neural network model provides better accuracy.
Knowledge distillation simplifies deep models into interpretable decision trees.
problem Interpretability of deep neural networks is challenging and important for practical deployment.
method Knowledge distillation applied to transform deep models into decision trees.
result The student model achieves better accuracy than vanilla decision trees.