English
Related papers

Related papers: Deletion and Insertion Tests in Regression Models

200 papers

Explainable AI (XAI) algorithms aim to help users understand how a machine learning model makes predictions. To this end, many approaches explain which input features are most predictive of a target label. However, such explanations can…

Human-Computer Interaction · Computer Science 2024-06-07 Jiaming Qu , Jaime Arguello , Yue Wang

Deep learning has shown superb performance in detecting objects and classifying images, ensuring a great promise for analyzing medical imaging. Translating the success of deep learning to medical imaging, in which doctors need to understand…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Lennart Brocki , Wistan Marchadour , Jonas Maison , Bogdan Badic , Panagiotis Papadimitroulas , Mathieu Hatt , Franck Vermet , Neo Christopher Chung

We formalise the widespread idea of interpreting neural network decisions as an explicit optimisation problem in a rate-distortion framework. A set of input features is deemed relevant for a classification decision if the expected…

Machine Learning · Computer Science 2019-05-28 Jan Macdonald , Stephan Wäldchen , Sascha Hauch , Gitta Kutyniok

EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target.…

Computer Vision and Pattern Recognition · Computer Science 2020-09-23 Yi-Shan Lin , Wen-Chuan Lee , Z. Berkay Celik

Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components.…

Machine Learning · Computer Science 2022-05-03 Talhat Khan , Kashif Ahmad , Jebran Khan , Imran Khan , Nasir Ahmad

With wide application of Artificial Intelligence (AI), it has become particularly important to make decisions of AI systems explainable and transparent. In this paper, we proposed a new Explainable Artificial Intelligence (XAI) method…

Artificial Intelligence · Computer Science 2025-04-01 Chi Zhao , Jing Liu , Elena Parilina

Deep learning has been successfully applied to medical image segmentation, enabling accurate identification of regions of interest such as organs and lesions. This approach works effectively across diverse datasets, including those with…

Image and Video Processing · Electrical Eng. & Systems 2025-04-08 Tianyi Ren , Juampablo Heras Rivera , Hitender Oswal , Yutong Pan , Agamdeep Chopra , Jacob Ruzevick , Mehmet Kurt

Explainability and evaluation of AI models are crucial parts of the security of modern intrusion detection systems (IDS) in the network security field, yet they are lacking. Accordingly, feature selection is essential for such parts in IDS…

Cryptography and Security · Computer Science 2024-10-15 Osvaldo Arreche , Tanish Guntur , Mustafa Abdallah

Feature selection is essential in the analysis of molecular systems and many other fields, but several uncertainties remain: What is the optimal number of features for a simplified, interpretable model that retains essential information?…

Machine Learning · Computer Science 2025-01-22 Romina Wild , Felix Wodaczek , Vittorio Del Tatto , Bingqing Cheng , Alessandro Laio

Kernel methods have been proven to be a powerful tool for the integration and analysis of highthroughput technologies generated data. Kernels offer a nonlinear version of any linear algorithm solely based on dot products. The kernelized…

Applications · Statistics 2024-11-27 Mitja Briscik , Marie-Agnès Dillies , Sébastien Déjean

In this paper we introduce a new feature selection algorithm to remove the irrelevant or redundant features in the data sets. In this algorithm the importance of a feature is based on its fitting to the Catastrophe model. Akaike information…

Machine Learning · Computer Science 2017-04-25 Mahdi Zarei

The applications of Artificial Intelligence (AI) methods especially machine learning techniques have increased in recent years. Classification algorithms have been successfully applied to different problems such as requirement…

Software Engineering · Computer Science 2023-02-13 Behnaz Jamasb , Reza Akbari , Seyed Raouf Khayami

Feature importance aims at measuring how crucial each input feature is for model prediction. It is widely used in feature engineering, model selection and explainable artificial intelligence (XAI). In this paper, we propose a new tree-model…

Machine Learning · Statistics 2020-09-17 Fan Fang , Carmine Ventre , Lingbo Li , Leslie Kanthan , Fan Wu , Michail Basios

Improving the interpretability of geospatial artificial intelligence (GeoAI) models has become critically important to open the "black box" of complex AI models, such as deep learning. This paper compares popular saliency map generation…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Chia-Yu Hsu , Wenwen Li

In recent years, Explainable AI (xAI) attracted a lot of attention as various countries turned explanations into a legal right. xAI allows for improving models beyond the accuracy metric by, e.g., debugging the learned pattern and…

Software Engineering · Computer Science 2022-10-05 Mohamed Karim Belaid , Eyke Hüllermeier , Maximilian Rabus , Ralf Krestel

Artificial Intelligence (AI) is often an integral part of modern decision support systems. The best-performing predictive models used in AI-based decision support systems lack transparency. Explainable Artificial Intelligence (XAI) aims to…

Machine Learning · Computer Science 2025-02-25 Tuwe Löfström , Helena Löfström , Ulf Johansson , Cecilia Sönströd , Rudy Matela

The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider…

Artificial Intelligence · Computer Science 2022-12-13 Yacine Izza , Xuanxiang Huang , Alexey Ignatiev , Nina Narodytska , Martin C. Cooper , Joao Marques-Silva

Explainable AI (XAI) methods are frequently applied to obtain qualitative insights about deep models' predictions. However, such insights need to be interpreted by a human observer to be useful. In this paper, we aim to use explanations…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Sunsheng Gu , Vahdat Abdelzad , Krzysztof Czarnecki

The integration of Artificial Intelligence (AI) in medical diagnostics is often hindered by model opacity, where high-accuracy systems function as "black boxes" without transparent reasoning. This limitation is critical in clinical…

Image and Video Processing · Electrical Eng. & Systems 2024-09-23 Pascal Passigan , Vayd Ramkumar

This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions. Concretely, this paper…

Machine Learning · Computer Science 2023-02-17 Xuanxiang Huang , Joao Marques-Silva