English
Related papers

Related papers: A model local interpretation routine for deep lear…

200 papers

Feature-attribution methods (e.g., SHAP, LIME) explain individual predictions but often miss higher-order structure: sets of features that act in concert. We propose Modules of Influence (MoI), a framework that (i) constructs a model…

Social and Information Networks · Computer Science 2025-11-03 Ehsan Moradi

LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the…

Machine Learning · Statistics 2019-11-01 Amir Hossein Akhavan Rahnama , Henrik Boström

Classifying the morphologies of radio galaxies is important to understand their physical properties and evolutionary histories. A galaxy's morphology is often determined by visual inspection, but as survey size increases robust automated…

Instrumentation and Methods for Astrophysics · Physics 2024-07-02 Emma Tolley

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based…

Machine Learning · Statistics 2024-04-15 Adam Spannaus , Heidi A. Hanson , Lynne Penberthy , Georgia Tourassi

We present a metric to quantify systematic labeling bias in galaxy morphology data sets stemming from the quality of the labeled data. This labeling bias is independent from labeling errors and requires knowledge about the intrinsic…

Astrophysics of Galaxies · Physics 2018-12-05 Guillermo Cabrera-Vives , Christopher J. Miller , Jeff Schneider

In this study, we examine over 14,000 radio galaxies finely selected from Radio Galaxy Zoo (RGZ) project and provide classifications for approximately 5,900 FRIs and 8,100 FRIIs. We present an analysis of these predicted radio galaxy…

Across various sectors applications of eXplainableAI (XAI) gained momentum as the increasing black-boxedness of prevailing Machine Learning (ML) models became apparent. In parallel, Large Language Models (LLMs) significantly developed in…

Computation and Language · Computer Science 2025-05-07 Jonas Bokstaller , Julia Altheimer , Julian Dormehl , Alina Buss , Jasper Wiltfang , Johannes Schneider , Maximilian Röglinger

This article addresses the challenge of validating the admission committee's decisions for undergraduate admissions. In recent years, the traditional review process has struggled to handle the overwhelmingly large amount of applicants'…

Machine Learning · Computer Science 2024-01-23 Amisha Priyadarshini , Barbara Martinez-Neda , Sergio Gago-Masague

Interpretability is often an essential requirement in medical imaging. Advanced deep learning methods are required to address this need for explainability and high performance. In this work, we investigate whether additional information…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Luisa Gallee , Meinrad Beer , Michael Goetz

The analysis of electrocardiogram (ECG) signals can be time consuming as it is performed manually by cardiologists. Therefore, automation through machine learning (ML) classification is being increasingly proposed which would allow ML…

Machine Learning · Computer Science 2022-05-10 Shourya Verma

In geophysics, hydrocarbon prospect risking involves assessing the risks associated with hydrocarbon exploration by integrating data from various sources. Machine learning-based classifiers trained on tabular data have been recently used to…

Machine Learning · Computer Science 2026-02-17 Prithwijit Chowdhury , Ahmad Mustafa , Mohit Prabhushankar , Ghassan AlRegib

Artificial intelligence (AI) is currently based largely on black-box machine learning models which lack interpretability. The field of eXplainable AI (XAI) strives to address this major concern, being critical in high-stakes areas such as…

Artificial Intelligence · Computer Science 2024-06-26 Sean Tull , Robin Lorenz , Stephen Clark , Ilyas Khan , Bob Coecke

The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying…

Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanations (LIME) has been a very popular framework for…

Machine Learning · Computer Science 2026-03-24 Mohamed Aymen Bouyahia , Argyris Kalogeratos

Many problems in computer vision have recently been tackled using models whose predictions cannot be easily interpreted, most commonly deep neural networks. Surrogate explainers are a popular post-hoc interpretability method to further…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Ricardo Kleinlein , Alexander Hepburn , Raúl Santos-Rodríguez , Fernando Fernández-Martínez

Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and LIME, while intuitive, may deviate from the model's…

Artificial Intelligence · Computer Science 2026-01-14 Caroline Mazini Rodrigues , Nicolas Boutry , Laurent Najman

Melanoma is one of the most aggressive and deadliest skin cancers, leading to mortality if not detected and treated in the early stages. Artificial intelligence techniques have recently been developed to help dermatologists in the early…

Machine Learning · Computer Science 2026-02-19 Wadduwage Shanika Perera , ABM Islam , Van Vung Pham , Min Kyung An

In this work we use variational inference to quantify the degree of uncertainty in deep learning model predictions of radio galaxy classification. We show that the level of model posterior variance for individual test samples is correlated…

Cosmology and Nongalactic Astrophysics · Physics 2022-02-09 Devina Mohan , Anna M. M. Scaife , Fiona Porter , Mike Walmsley , Micah Bowles

Unknown class distributions in unlabelled astrophysical training data have previously been shown to detrimentally affect model performance due to dataset shift between training and validation sets. For radio galaxy classification, we…

Astrophysics of Galaxies · Physics 2022-07-19 Inigo Val Slijepcevic , Anna M. M. Scaife , Mike Walmsley , Micah Bowles

We present early results from Radio Galaxy Zoo, a web-based citizen science project for visual inspection and classification of images from all-sky radio surveys. The goals of the project are to classify individual radio sources…

Astrophysics of Galaxies · Physics 2016-03-09 Kyle W. Willett