Zobrazeno 1 - 10
of 2 608
pro vyhledávání: '"Wright, A. N."'
Many existing interpretation methods are based on Partial Dependence (PD) functions that, for a pre-trained machine learning model, capture how a subset of the features affects the predictions by averaging over the remaining features. Notable methods
Externí odkaz:
http://arxiv.org/abs/2410.13448
Autor:
Burk, Lukas, Zobolas, John, Bischl, Bernd, Bender, Andreas, Wright, Marvin N., Sonabend, Raphael
This work presents the first large-scale neutral benchmark experiment focused on single-event, right-censored, low-dimensional survival data. Benchmark experiments are essential in methodological research to scientifically compare new and existing mo
Externí odkaz:
http://arxiv.org/abs/2406.04098
Autor:
Ewald, Fiona Katharina, Bothmann, Ludwig, Wright, Marvin N., Bischl, Bernd, Casalicchio, Giuseppe, König, Gunnar
Publikováno v:
Longo, L., Lapuschkin, S., Seifert, C. (eds) Explainable Artificial Intelligence. xAI 2024. Communications in Computer and Information Science, vol 2154. Springer, Cham
While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires insights into feature-target associations, which many
Externí odkaz:
http://arxiv.org/abs/2404.12862
Autor:
Koenen, Niklas, Wright, Marvin N.
In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial for high-s
Externí odkaz:
http://arxiv.org/abs/2404.11330
Autor:
Langbein, Sophie Hanna, Krzyziński, Mateusz, Spytek, Mikołaj, Baniecki, Hubert, Biecek, Przemysław, Wright, Marvin N.
With the spread and rapid advancement of black box machine learning models, the field of interpretable machine learning (IML) or explainable artificial intelligence (XAI) has become increasingly important over the last decade. This is particularly re
Externí odkaz:
http://arxiv.org/abs/2403.10250
Autor:
Blesch, Kristin, Wright, Marvin N.
This paper introduces $\textit{arfpy}$, a python implementation of Adversarial Random Forests (ARF) (Watson et al., 2023), which is a lightweight procedure for synthesizing new data that resembles some given data. The software $\textit{arfpy}$ equips
Externí odkaz:
http://arxiv.org/abs/2311.07366
Autor:
Spytek, Mikołaj, Krzyziński, Mateusz, Langbein, Sophie Hanna, Baniecki, Hubert, Wright, Marvin N., Biecek, Przemysław
Publikováno v:
Bioinformatics, 39(12):btad723, 2023
Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their
Externí odkaz:
http://arxiv.org/abs/2308.16113
Autor:
Koenen, Niklas, Wright, Marvin N.
The R package innsight offers a general toolbox for revealing variable-wise interpretations of deep neural networks' predictions with so-called feature attribution methods. Aside from the unified and user-friendly framework, the package stands out in
Externí odkaz:
http://arxiv.org/abs/2306.10822
Global feature effect methods, such as partial dependence plots, provide an intelligible visualization of the expected marginal feature effect. However, such global feature effect methods can be misleading, as they do not represent local feature effe
Externí odkaz:
http://arxiv.org/abs/2306.00541
Autor:
Archer, M. O., Hartinger, M. D., Rastaetter, L., Southwood, D. J., Heyns, M., Eggington, J. W. B., Wright, A. N., Plaschke, F., Shi, X.
Publikováno v:
Journal of Geophysical Research: Space Physics, 128, e2022JA031081
Surface waves on Earth's magnetopause have a controlling effect upon global magnetospheric dynamics. Since spacecraft provide sparse in situ observation points, remote sensing these modes using ground-based instruments in the polar regions is desirab
Externí odkaz:
http://arxiv.org/abs/2303.01138