CNN improves salt body interpretation in seismic imaging.
problem Manual salt body interpretation is time-consuming and prone to bias.
method U-Net and ResNet with ELU activation and Lovász-Softmax loss.
result CNN predictions match manual interpretations well, especially in weak reflection areas.
SALT models combine ARHMM and SLDS for efficient, interpretable time-series analysis.
problem Efficient modeling of systems with time-varying dynamics and long-range dependencies.
method Switching autoregressive low-rank tensor models parameterized with a low-rank factorization.
result SALT models provide a balance of interpretability and efficiency, outperforming ARHMMs and SLDSs.
Deep learning improves salt deposits segmentation in seismic data.
problem Segmenting salt deposits in seismic reflection data for hydrocarbon exploration.
method A novel deep learning approach combining U-Net with ResNeXt-50 encoder, Spatial-Channel Squeeze & Excitation, Lovasz loss, CoordConv, and Hypercolumn methods.
result Achieved 27th place in Kaggle competition for salt deposits segmentation.
Neural network enhances seismic imaging in salt-prone areas.
problem Improving velocity model building for faster FWI convergence.
method 3D convolutional, de-convolutional, and max-pooling neural network architecture with data augmentations and regularization.
result Proposed neural network generates salt body probability cubes for FWI regularization.
SALT combines geometric and model-based alignment for domain adaptation.
problem Aligning source and target domains for unsupervised domain adaptation.
method SALT treats alignment as an auxiliary task, leveraging subspace geometry and gradient-based optimization.
result SALT achieves comparable or better performance than state-of-the-art methods.
Machine learning predicts rock properties from routine core analysis.
problem Predict rock properties like porosity and permeability from routine core analysis.
method Developed and compared machine learning models (NN, SVM, LR).
result Neural network with hidden layers best for all rock properties.
A new greedy method tackles ℓ0,∞ sparse coding for better image processing.
problem Imbalanced sparsity in ℓ0 and ℓ1 norms for image processing. method Greedy matching pursuit for ℓ0,∞ norm optimization. result Efficient method for ℓ0,∞ sparse coding and dictionary learning. BYOV combines SSL and Bayesian methods for uncertainty estimation.
problem Model uncertainty in applications.
method Combines Bootstrap Your Own Latent (BYOL) and Bayes by Backprop (BBB).
result BYOV improves model calibration and reliability with various augmentations.
The prediction of the gas production from mature gas wells, due to their complex end-of-life behavior, is challenging and crucial for operational decision making. In this paper, we apply a modified deep LSTM model for prediction of the gas flow rates in mature gas wells, including the uncertainties in input parameters.…
Paper proposes a technique to detect and predict sources of contaminants in complex systems.
problem Difficulty in identifying sources of contaminants in coupled natural and human systems.
method Developed a technique for simultaneous source detection and prediction.
result Outperforms other approaches in detecting potential groundwater contamination.
New method for sparse data using L1-NMF with improved sparsity control.
problem Sparse data with false zeros and heavy-tailed noise.
method Component-wise L1-NMF with weighted penalization and coordinate descent.
result Effective in handling sparse data with false zeros.
Split-BN improves SSL by separating BN stats for unlabeled data.
problem SSL benefits from unlabeled data are often lost or even harmful when class mismatch exists.
method Split-BN uses separate BN statistics for unlabeled data.
result Split-BN improves SSL performance in shifted domain settings.
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using three well known DNNs (ResNet-152, VGG-19, GoogLeNet) we find the human visual system to be more robust to nearly all of the tested image manip…
Deep learning detects icebergs and ships from SAR data.
problem Detecting icebergs and ships from SAR data for Arctic navigation safety.
method Transfer Learning with a CNN, augmented data, and multiple outputs.
result Significant accuracy boost (logarithmic score 0.1463) in iceberg and ship detection.
Machine learning corrects ion interference in nutrient solutions.
problem Ion imbalance and excessive salt accumulation in hydroponic systems.
method Machine learning approach to correct ion sensor data affected by ion interference.
result Readjusted ion sensor data showed high accuracy (91.6-98.3%).
We make posterior sampling in FWI feasible for large surveys.
problem Uncertainty-aware subsurface models at field scale.
method Coupling diffusion-based posterior sampling with simultaneous-source FWI data.
result Lower model error and better data fit at reduced computational cost.
New definition of interpretability makes model design more actionable.
problem Current definitions of interpretability are not actionable and inform users poorly.
method Proposes a new definition of interpretability that is general, simple, and actionable.
result New definition reveals necessary properties for designing interpretable models.
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.
Interpretability of ML models improves healthcare decisions.
problem Ensuring machine learning models are understandable for healthcare users.
method Classifying interpretability into local and global approaches, and model-specific vs. model-agnostic methods.
result Examples of practical interpretability in healthcare, including prediction and treatment optimization.
VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.
problem Lack of higher-level structure interpretation in FLMs' attention weights.
method Formal definition of conceptual interpretation, variational Bayesian framework (VALC).
result VALC finds optimal language concepts for FLM predictions, providing concept-level interpretations.
New framework improves interpretability of trainable prompts.
problem Improving task-specific LLM performance with soft prompts remains a black-box method.
method Developed a theoretical framework for evaluating interpretability of trainable prompts, inspired new objective functions.
result Found a fundamental trade-off between interpretability and task performance in trainable prompts.
Interpreting machine learning models helps understand adversarial attacks and defenses.
problem Understanding model vulnerability to adversarial attacks.
method Model interpretation techniques to explore adversarial attacks and defenses.
result Interpretation methods can be applied to adversarial attacks and defenses.
Proposes a decision-theoretic approach for enhancing model interpretability in Bayesian frameworks.
problem Challenges the traditional approach of restricting model structure for interpretability in Bayesian frameworks.
method Introduces an interpretability utility function and a two-step method involving a reference model and a proxy model.
result Demonstrates that the proposed method generates more accurate models with the same level of interpretability.
Study on trade-offs between accuracy and interpretability in machine learning.
problem Lack of formal study on statistical cost of interpretability.
method Modeling interpretability as a constraint in empirical risk minimization for binary classification.
result Explains conditions under which accuracy trade-off occurs with interpretability constraints.
Model-agnostic interpretation methods can mislead if not used carefully.
problem Misinterpretation of machine learning models due to improper use of techniques.
method General pitfalls of model-agnostic interpretation methods.
result Many pitfalls exist when using global interpretation techniques for machine learning models.
Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and s…
New framework learns interpretable rule ensembles without sacrificing accuracy.
problem Trade-off between accuracy and interpretability in rule ensembles.
method Introduces local interpretability and a regularizer to promote it, using coordinate descent with local search.
result Learns rule ensembles with fewer rules to explain individual predictions, maintaining comparable accuracy.
Study finds machine learning interpretations are often unstable and unreliable.
problem Reliability of machine learning interpretations in high-stakes domains.
method Stability study on global interpretations using tabular data.
result Popular interpretation methods are frequently unstable, less stable than predictions, and not associated with prediction accuracy.
InterpretML simplifies machine learning interpretability for users and researchers.
problem Making machine learning models understandable to non-experts.
method Unified Python package exposing interpretability algorithms and visualization.
result First implementation of Explainable Boosting Machine, a powerful, interpretable model.
Regularizes black-box models to improve interpretability.
problem Improving interpretability of black-box models without sacrificing accuracy.
method Regularizes a black-box model at training time to connect model explainability, explanation system, and quality metrics.
result Substantial improvement in explanation fidelity and stability across various datasets and explanation systems, with slight accuracy trade-off.
Meta-learning approach to learn interpretable models from human feedback.
problem Tackling the challenge of making machine learning models interpretable.
method A meta-learning approach where a model of non-trivial proxies of human interpretability is learned from human feedback, then incorporated into the ML training process to optimize for interpretability.
result The approach leads to formulas that are either significantly more or equally accurate while being more interpretable.
This paper optimizes clustering interpretability by balancing value and user-defined features.
problem Generating interpretable clusters in graph data.
method Proposes a β-interpretable clustering algorithm that ensures at least β fraction of nodes share the same feature value.
result Empirical demonstration of the benefits of the proposed approaches in generating interpretable clusters.
Boosted trees improve reinforcement learning solutions that are easy to understand.
problem Creating accurate reinforcement learning solutions that are also easy to understand.
method Using boosted regression trees to combine multiple regression trees.
result Boosted regression trees produce solutions that are as accurate as other methods but are also easy to understand.
We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.
Certifiable defense method improves robustness of deep learning interpretation.
problem Vulnerability of gradient-based saliency maps to adversarial attacks.
method Sparsified SmoothGrad method, extending certifiably robust smooth classifier bounds.
result Sparsified SmoothGrad method is certifiably robust against adversarial perturbations.
Proposes a model to interpret complex ML algorithms.
problem Complex ML models are hard to interpret.
method Uses model-based regression trees and interpretable main-effects models.
result Surrogate model provides interpretable results with good predictive performance.
We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required. In this work, we optimize for interpretability by directly including humans in the …
As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpr…
New method learns to encode predictions within interpretations, improving evaluation.
problem Need for interpretable machine learning, but existing methods are slow or lack fidelity.
method Amortized explanation methods that learn a global selector model optimizing fidelity of interpretations.
result Predictions can be encoded within interpretations, detected by EVAL-X.
The paper defines a mathematical framework for measuring model interpretability.
problem Improving trust and understanding in machine learning models for complex decisions.
method Constructing interpretable steps in a sequence for various models, generalizing to a family of consistent measures.
result A formal definition of interpretability allows quantifying the tradeoff with predictive accuracy.
LIMIS improves locally interpretable models by selecting and distilling key instances.
problem Low fidelity of locally interpretable models.
method LIMIS uses instance-wise subsampling guided by policy gradient and reward to improve fidelity.
result LIMIS near-matches black-box model accuracy while significantly improving fidelity.
GMT improves interpretability of XGNNs by approximating SubMT.
problem Limited understanding of existing interpretable subgraph learning methods.
method Formulated subgraph multilinear extension (SubMT) and designed GMT architecture.
result GMT outperforms state-of-the-art in both interpretability and generalizability.
Paper proposes a method to improve interpretability in kernel learning models.
problem Improving interpretability in flexible machine learning models.
method Proposes a quantitative index for interpretability and a universal learning framework to balance interpretability and generalization performance.
result Demonstrates a method to achieve global optimal solution in balancing interpretability and generalization performance.
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.
Hybrid model combines interpretable and black-box models for better transparency and performance.
problem Balancing interpretability and predictive performance in machine learning models.
method Proposes a Hybrid Predictive Model (HPM) integrating an interpretable model with a black-box model, using principled objective functions and customized training algorithms.
result Hybrid models achieve an efficient trade-off between transparency and predictive performance.
Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitiv…
Tutorial on interpreting SPECT images for PD recognition using AI.
problem Difficulty in interpreting complex DL models for clinical use.
method Evaluation of six interpretation methods on four DCNN architectures.
result Guided backpropagation and SHAP methods are suitable for PD recognition.
Study assesses human interpretability of machine learning models.
problem Ensuring machine learning models are understandable by humans.
method User study with 1,000 participants testing simulatability and 'what if' local explainability.
result Increased runtime operation count correlates with decreased human accuracy on local interpretability tasks.