Výsledky vyhledávání - "Jarke J. van Wijk"

StrategyAtlas: Strategy Analysis for Machine Learning Interpretability

Autor: Dennis Collaris, Jarke J. van Wijk

Publikováno v: IEEE Transactions on Visualization and Computer Graphics, 29(6), 2996-3008. IEEE Computer Society

Businesses in high-risk environments have been reluctant to adopt modern machine learning approaches due to their complex and uninterpretable nature. Most current solutions provide local, instance-level explanations, but this is insufficient for unde

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e38b85487978e684bc5bd30a97d7baf
http://www.scopus.com/inward/record.url?scp=85124079061&partnerID=8YFLogxK

Zobrazit plný text záznamu

Comparative Evaluation of Contribution-Value Plots for Machine Learning Understanding

Autor: Jarke J. van Wijk, Dennis Collaris

Publikováno v: Journal of Visualization, 25(1), 47-57. Springer

Abstract The field of explainable artificial intelligence aims to help experts understand complex machine learning models. One key approach is to show the impact of a feature on the model prediction. This helps experts to verify and validate the pred

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::634ca366b1694b5a5a583a40086b5e0a
https://doi.org/10.1007/s12650-021-00776-w

Zobrazit plný text záznamu

LEMON: Alternative Sampling for More Faithful Explanation Through Local Surrogate Models

Autor: Dennis Collaris, Pratik Gajane, Joost Jorritsma, Jarke J. van Wijk, Mykola Pechenizkiy

Publikováno v: Advances in Intelligent Data Analysis XXI ISBN: 9783031300462

Local surrogate learning is a popular and successful method for machine learning explanation. It uses synthetic transfer data to approximate a complex reference model. The sampling technique used for this transfer data has a significant impact on the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3087c7d0868807db5bbda6f9fbeda65b
https://doi.org/10.1007/978-3-031-30047-9_7

Zobrazit plný text záznamu

Characterizing Data Scientists' Mental Models of Local Feature Importance

Autor: Dennis Collaris, Hilde J.P. Weerts, Daphne Miedema, Jarke J. van Wijk, Mykola Pechenizkiy

Publikováno v: NordiCHI '22: Nordic Human-Computer Interaction Conference

Feature importance is an approach that helps to explain machine learning model predictions. It works through assigning importance scores to input features of a particular model. Different techniques exist to derive these scores, with widely varying u

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f4e82ada25ff19fe3974489b670bce8
http://www.scopus.com/inward/record.url?scp=85140928779&partnerID=8YFLogxK

Zobrazit plný text záznamu

II-20: Intelligent and pragmatic analytic categorization of image collections

Autor: Marcel Worring, Jarke J. van Wijk, Jan Zahálka

Publikováno v: IEEE Transactions on Visualization and Computer Graphics, 27(2):9230430, 422-431. IEEE Computer Society
arXiv, 2020:2005.02149. Cornell University Library

We introduce II-20 (Image Insight 2020), a multimedia analytics approach for analytic categorization of image collections. Advanced visualizations for image collections exist, but they need tight integration with a machine model to support analytic c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a69a090383dbe0ae81e8ac2fddb63a3
https://doi.org/10.1109/TVCG.2020.3030383

Zobrazit plný text záznamu

Family metro maps

Autor: Verus Pronk, Jan Korst, Jarke J. van Wijk

Publikováno v: Journal of Visualization, 25(2). Springer

We present family metro maps as a new approach to visualize the relations between multiple related families. A family is represented by a metro line, where the parents are the end nodes and the children the intermediate nodes. We introduce family tre

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05cb36d9fbbbe3e9e5b0e357c52fcdb1
http://www.scopus.com/inward/record.url?scp=85116491867&partnerID=8YFLogxK

Zobrazit plný text záznamu

STBins

Autor: Vincent Bloemen, Ji Qi, Huub van de Wetering, Jarke J. van Wijk, Shihan Wang

Publikováno v: IEEE transactions on visualization and computer graphics, 26(1):8805450, 1054-1063. IEEE
IEEE Transactions on Visualization and Computer Graphics, 26(1):8805450, 1054-1063. IEEE Computer Society
IEEE Transactions on visualization and computer graphics, 26(1), 1054-1063. IEEE Computer Society

While analyzing multiple data sequences, the following questions typically arise: how does a single sequence change over time, how do multiple sequences compare within a period, and how does such comparison change over time. This paper presents a vis

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b56fcef0c5d5e624a8ea74c0163cf97
https://doi.org/10.1109/tvcg.2019.2934289

Zobrazit plný text záznamu

V‐Awake: A Visual Analytics Approach for Correcting Sleep Predictions from Deep Learning Models

Autor: Michel A. Westenberg, Jarke J. van Wijk, Binyam Gebrekidan Gebre, Humberto S. Garcia Caballero

Publikováno v: Computer Graphics Forum. 38:1-12

The usage of deep learning models for tagging input data has increased over the past years because of their accuracy and high performance. A successful application is to score sleep stages. In this scenario, models are trained to predict the sleep st

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1bdf3fdf03b35c84d0ac88c2fe566bb8
https://doi.org/10.1111/cgf.13667

Zobrazit plný text záznamu

Plný text ve formátu HTML

A visualization of family relations inspired by the London metro map

Autor: Jan Korst, Verus Pronk, Jarke J. van Wijk

Publikováno v: VINCI

We propose a new visualization of family relations, called family metro map, which is inspired by the famous London Underground Map. A family is represented by a metro line, where the parents are the end nodes and the children the intermediate nodes.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::31613481bc768ab82117defce587b242
https://doi.org/10.1145/3430036.3430065

Zobrazit plný text záznamu

Machine learning interpretability through contribution-value plots

Autor: Jarke J. van Wijk, Dennis Collaris

Publikováno v: VINCI

The field of explainable artificial intelligence aims to help experts understand complex machine learning models. One key approach is to show the impact of a feature on the model prediction. This helps experts to verify and validate the predictions t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e76aae547792cbcb856aa74102df0e0f
https://doi.org/10.1145/3430036.3430067

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání