Interpretable classifier improves accuracy through probability series expansion.
problem Improving classifier accuracy while maintaining interpretability.
method Directly measures class probabilities from training data, refines predictions through series expansion.
result Achieves comparable accuracy to Random Forests on four datasets.
CLE explains any classifier predictions in plain terms.
problem Understanding complex classifier predictions.
method Model-agnostic explanation technique approximating locally using interpretable models.
result CLE provides faithful and interpretable explanations for various classifiers.
Novel approach for creating interpretable classifiers using bilevel optimization of split-rules in NLDTs.
problem Creating highly accurate and easily interpretable classifiers for practical applications.
method Representing classifiers as assemblies of simple mathematical rules using NLDTs with evolutionary bilevel optimization.
result The approach ensures interpretability while achieving high accuracy on various classification problems.
Deep learning model interprets diabetic retinopathy severity levels.
problem Lack of interpretability in deep learning models for medical diagnosis.
method Developed an interpretable classifier using deep learning with explanations for each pixel.
result Generated visual maps for expert interpretation of model's decisions.
Paper explains classifier predictions without classifier or data info.
problem Explain classifier predictions without classifier or data info.
method Instance-based approach using Growing Spheres algorithm with sparsity constraint.
result Minimal changes needed to alter a prediction identified.
The paper analyzes methods to identify influential data points in deep models.
problem Interpreting deep learning models and debugging datasets.
method Curated experiments to analyze influence of data points on classifiers.
result Training loss-based sample selection outperformed other methods in detecting mislabels.
Paper presents a method to extract and interpret knowledge from a spiking neural classifier.
problem Extracting and interpreting knowledge from a spiking neural classifier with time-varying synaptic weights.
method The method involves encoding real-valued input data into spike patterns, training the classifier, and mapping the weighted postsynaptic potential to feature strength functions (FSFs).
result The FSFs represent the extracted knowledge from the classifier and can be used for classification and interpretation.
The paper introduces a method to find multiple interpretable classifiers from a dataset.
problem Finding multiple accurate classifiers that are also interpretable.
method Introduces a method to identify a maximal set of distinct but accurate models for a dataset.
result Empirically demonstrates simpler, more interpretable classifiers are recovered.
New algorithm improves interpretability in sequence classification.
problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.
Machine-generated interpretations do not improve users' guessing accuracy in image classifiers.
problem Determining the usefulness of machine-generated explanations for deep neural networks.
method Human evaluation of crowd workers guessing incorrectly predicted labels with and without visual interpretations.
result Showing machine-generated visual interpretations decreased average guessing accuracy by about 10%.
ASTRID method interprets classifier interactions in datasets.
problem Understanding attribute interactions in classification models.
method ASTRID method for investigating attribute interactions.
result ASTRID reveals associations between attributes for better model interpretability.
Interpretable semi-supervised classifier for black-box models with two self-labeling strategies.
problem Lack of labeled data and difficulty in explaining black-box models.
method Combines black-box and white-box approaches for self-labeling and prediction.
result Superior prediction rates and interpretability compared to state-of-the-art classifiers.
A student classifier learns from feature visualizations of a teacher network to achieve high accuracy.
problem Machine learning-based sleep apnea detection with limited access to training data.
method Interpretation-based indirect knowledge transfer using activation maximization and synthetic datasets.
result The student classifier achieves 97.8% accuracy on MNIST and 86.1-89.5% on Apnea-ECG dataset.
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.
DarkSight visualizes deep classifiers more effectively than t-SNE.
problem Interpreting black box classifiers like deep networks.
method DarkSight embeds data points into a low-dimensional space to compress deep classifiers, using dark knowledge for a new confidence measure.
result DarkSight visualizations are more informative and yield a new confidence measure.
New algorithms improve time series classification accuracy and efficiency while enhancing interpretability.
problem Lack of interpretability in time series classification algorithms.
method Combining multiple resolutions and domains, using SEQL with greedy feature selection.
result SAX-SFA-SEQL achieves similar accuracy to state-of-the-art methods but with lower computational time.
Model interprets image classification using hierarchical prototypes.
problem Lack of hierarchical interpretation in vision models.
method Uses hierarchically organized prototypes to classify objects at each level of a taxonomy.
result Model interprets image classification at each level of the taxonomy.
A decoder helps interpret neural network layers.
problem Understanding the output of neural network layers.
method Developed a Classifier-Decoder (ClaDec) architecture.
result Reconstructed images from ClaDec are more relevant for classification.
Anchors explains text classifiers by highlighting key words.
problem Interpreting machine learning models, especially for text classifiers.
method Formalizes Anchors' algorithm and analyzes its behavior on linear text classifiers.
result Anchors produces meaningful results on linear text classifiers.
TSInsight improves interpretability of deep time-series models.
problem Lack of interpretability methods for time-series data.
method Attach auto-encoder to classifier with sparsity-inducing norm, fine-tune based on gradients and reconstruction penalty.
result TSInsight effectively boosts interpretability of deep time-series models.
A model finds interpretable prototypes for MIL datasets.
problem Finding interpretable prototypes for multiple instance learning.
method Permutation invariant maximally predictive prototype generator.
result The model outperforms existing approaches in accuracy and efficiency.
Tensor networks preserve data interpretability for supervised learning.
problem Efficiently classifying data using tensor networks.
method Number-state preserving tensor networks for supervised learning.
result Number-state preserving tensor networks can be trained to maximize their scalar product against data sets.
This paper identifies key independent causes for diabetic retinopathy classification using deep learning.
problem Difficulty in interpreting deep learning models for medical diagnosis.
method Combining Independent Component Analysis with Score Visualization.
result Only 3 independent components are needed for classifying diabetic retinopathy.
Deep networks can be understood as logical circuits, improving interpretability and generalization.
problem Lack of interpretability in deep neural networks.
method Hierarchical decomposition of DNN discrete classification map into logical combinations of intermediate classifiers.
result Deep networks can be interpreted as logical circuits with improved generalization.
Interpretable ML models for missing data and visualisation.
problem Understanding and evaluating fairness in ML models.
method Introduced angle-based variants of Learning Vector Quantization (LVQ) models.
result Models can handle missing values and extract knowledge from datasets.
Ensembles of decision trees perform well on many problems, but are not interpretable. In contrast to existing approaches in interpretability that focus on explaining relationships between features and predictions, we propose an alternative approach to interpret tree ensemble classifiers by surfacing representative poin…
EUREKA builds classifiers that use surprising features.
problem Building classifiers that are interesting, not just accurate.
method Uses large language models to rank features by interestingness and builds interpretable classifiers using only selected features.
result EUREKA discovers non-obvious yet predictive features, improving accuracy and offering insights.
Semantic embeddings improve safety-critical classifier performance.
problem Improving interpretability and error detection in safety-critical neural networks.
method Created embeddings from symbolic domain knowledge, used for misprediction interpretation and error detection, introduced semantic distance for confidence measurement.
result Semantic distance achieves near state-of-the-art performance in a traffic sign classifier, faster than other methods.
Proposes method for global explanations of credit risk models.
problem Lack of interpretability in credit risk scoring models.
method Sampling decision function to learn interpretable models.
result Unified solution to approximate complex decision boundaries.
Interpretable deep learning classifies two-prong jets using jet spectra.
problem Lack of interpretability in deep learning for jet classification.
method Truncated Taylor series jet spectrum for interpretability.
result Interpretable network performs similarly to CNN but is simpler.
This paper improves NLP interpretability by using sentence segments instead of words.
problem Limitations of word-based sampling in explaining complex BERT models.
method Using sentence segments as elementary building blocks for NLP interpretability.
result Improved fidelity of the explainer on a benchmark classification task.
New linear models improve time series classification efficiency and interpretability.
problem Complex and inefficient classifiers limit interpretability and applicability to variable-length time series.
method Symbolic representations, multi-resolution, multi-domain, linear models.
result mtSS-SEQL+LR achieves similar accuracy to state-of-the-art methods but with lower time and memory usage.
Regularized discriminant analysis (RDA), proposed by Friedman (1989), is a widely popular classifier that lacks interpretability and is impractical for high-dimensional data sets. Here, we present an interpretable and computationally efficient classifier called high-dimensional RDA (HDRDA), designed for the small-sampl…
The main result of this paper is a new classification theorem for links (smooth embeddings in codimension 2). The classifying space is the rack space (defined in [Trunks and classifying spaces, Applied Categorical Structures, 3 (1995) 321--356]) and the classifying bundle is the first James bundle (defined in "James bu…
Interpretable companion model for black-box classifiers.
problem Dilemma between interpretable and black-box models.
method Trains a companion model from data and black-box model predictions, optimizing a combination of accuracy and complexity.
result Companion model provides interpretable predictions with a slight accuracy loss for user choice.
CoDA Nets improve interpretability in neural networks.
problem Improving interpretability in neural networks.
method Dynamic Alignment Units (DAUs) for input-dependent linear transformations.
result CoDA Nets achieve on par results with ResNet and VGG models on complex datasets.
r-STSF improves TSC accuracy and interpretability.
problem Lack of interpretability in state-of-the-art TSC methods.
method Randomized-Supervised Time Series Forest (r-STSF) using interval-based approach and ensemble of randomized trees.
result r-STSF achieves state-of-the-art accuracy and enables interpretability.
ICLabel automates EEG IC classification, improving accuracy and speed.
problem Manual IC classification is time-consuming and requires expertise.
method Automated classifier using crowdsourced labels and improved efficiency.
result ICLabel classifier outperforms existing methods in accuracy and speed.
Develops a framework to copy any machine learning classifier without prior knowledge.
problem Copying machine learning classifiers without access to their parameters or training data.
method Theory and framework development, synthetic set generation, loss identification, and evaluation metrics.
result Copies can enhance existing solutions and add new features.
New theory shows interpretable models can outperform black-box models in decision-making systems.
problem The importance of interpretability in machine learning models.
method Characterized performance of two-node data fusion systems using distributed detection theory.
result A human with an interpretable classifier outperforms one with a black-box classifier.
We introduce a new metric to evaluate corruption robustness of ML classifiers.
problem Evaluating corruption robustness of machine learning classifiers.
method We propose a test data augmentation method using minimal class separation distance to derive a robustness distance ε and a metric MSCR.
result The MSCR metric allows interpretable comparison of classifier robustness on different datasets.
Proposes ConRad model for lung cancer classification using radiomics and interpretable machine learning.
problem Lack of interpretability in deep neural networks for cancer diagnosis.
method Integration of radiomics and DNN-predicted biomarkers in interpretable classifiers (ConRad).
result ConRad models outperform CNNs in five-fold cross-validation.
IntroVAC learns interpretable latent subspaces for better image quality.
problem Difficulties in interpreting latent spaces and limitations in image generation.
method Introspective Variational Classifier (IntroVAC) using additional labels and adversarial training.
result Improved image quality and meaningful latent directions for fine-grained manipulation.
A new model SEQ clusters and classifies encoded features for better interpretability.
problem Lack of interpretability in classical supervised classification tasks.
method Proposes a novel supervised learning model named Supervised-Encoding Quantizer (SEQ) that applies a quantizer to cluster and classify encoded features.
result The quantizer provides an interpretable graph where each cluster represents a class with a particular style.
Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors, low signal to noise ratios, and the high dimensionality of neuroimaging data. T…
Paper proposes a classifier that optimizes utility function with prior knowledge.
problem Designing a classifier that optimizes a utility function based on prior knowledge.
method Systematic framework incorporating prior knowledge to optimize a utility function.
result The classifier asymptotically converges to the optimal classifier (Bayes rule) as data size grows.
Combining interpretability and stability methods improves DNN robustness.
problem Improving interpretability and robustness of deep neural networks.
method Combining interpretability (conductance) and stability (binary classifier) methods to detect and discard wrong predictions.
result Combining interpretability and stability methods increases model robustness.
New samplers improve compositional generation with diffusion models.
problem Improving compositional generation with diffusion models.
method Score-based interpretation, energy-based parameterization, Metropolis-corrected samplers.
result New samplers enable successful compositional generation across various tasks.