Výsledky vyhledávání - "Budding, Céline"

Report

Benchmark data to study the influence of pre-training on explanation performance in MR image classification

Autor: Oliveira, Marta, Wilming, Rick, Clark, Benedict, Budding, Céline, Eitel, Fabian, Ritter, Kerstin, Haufe, Stefan

Convolutional Neural Networks (CNNs) are frequently and successfully used in medical prediction tasks. They are often used in combination with transfer learning, leading to improved performance when training data for the task are scarce. The resultin

Externí odkaz: http://arxiv.org/abs/2306.12150

Zobrazit plný text záznamu

Report

Evaluating saliency methods on artificial data with different background types

Autor: Budding, Céline, Eitel, Fabian, Ritter, Kerstin, Haufe, Stefan

Over the last years, many 'explainable artificial intelligence' (xAI) approaches have been developed, but these have not always been objectively evaluated. To evaluate the quality of heatmaps generated by various saliency methods, we developed a fram

Externí odkaz: http://arxiv.org/abs/2112.04882

Zobrazit plný text záznamu

Report

Scrutinizing XAI using linear ground-truth data with suppressor variables

Autor: Wilming, Rick, Budding, Céline, Müller, Klaus-Robert, Haufe, Stefan

Machine learning (ML) is increasingly often used to inform high-stakes decisions. As complex ML models (e.g., deep neural networks) are often considered black boxes, a wealth of procedures has been developed to shed light on their inner workings and

Externí odkaz: http://arxiv.org/abs/2111.07473

Zobrazit plný text záznamu