�ݺ�ߣshows by User: MartijnWillemsen

�ݺ�ߣshows by User: MartijnWillemsen / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: MartijnWillemsen / Tue, 05 Jul 2022 09:11:45 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: MartijnWillemsen Explainability in AI and Recommender systems: let’s make it interactive! /slideshow/explainability-in-ai-and-recommender-systems-lets-make-it-interactive/252124352 exuminvitedtalk-220705091145-12e6cd67
invited talk in the ExUM workshop in the UMAP 2022 conference abstract: Explainability has become an important topic both in Data Science and AI in general and in recommender systems in particular, as algorithms have become much less inherently explainable. However, explainability has different interpretations and goals in different fields. For example, interpretability and explanainability tools in machine learning are predominantly developed for Data Scientists to understand and scrutinize their models. Current tools are therefore often quite technical and not very ‘user-friendly’. I will illustrate this with our recent work on improving the explainability of model-agnostic tools such as LIME and SHAP. Another stream of research on explainability in the HCI and XAI fields focuses more on users’ needs for explainability, such as contrastive and selective explanations and explanations that fit with the mental models and beliefs of the user. However, how to satisfy those needs is still an open question. Based on recent work in interactive AI and machine learning, I will propose that explainability goes together with interactivity, and will illustrate this with examples from our own work in music genre exploration, that combines visualizations and interactive tools to help users understand and tune our exploration model.]]>
invited talk in the ExUM workshop in the UMAP 2022 conference abstract: Explainability has become an important topic both in Data Science and AI in general and in recommender systems in particular, as algorithms have become much less inherently explainable. However, explainability has different interpretations and goals in different fields. For example, interpretability and explanainability tools in machine learning are predominantly developed for Data Scientists to understand and scrutinize their models. Current tools are therefore often quite technical and not very ‘user-friendly’. I will illustrate this with our recent work on improving the explainability of model-agnostic tools such as LIME and SHAP. Another stream of research on explainability in the HCI and XAI fields focuses more on users’ needs for explainability, such as contrastive and selective explanations and explanations that fit with the mental models and beliefs of the user. However, how to satisfy those needs is still an open question. Based on recent work in interactive AI and machine learning, I will propose that explainability goes together with interactivity, and will illustrate this with examples from our own work in music genre exploration, that combines visualizations and interactive tools to help users understand and tune our exploration model.]]> Tue, 05 Jul 2022 09:11:45 GMT /slideshow/explainability-in-ai-and-recommender-systems-lets-make-it-interactive/252124352 MartijnWillemsen@slideshare.net(MartijnWillemsen) Explainability in AI and Recommender systems: let’s make it interactive! MartijnWillemsen invited talk in the ExUM workshop in the UMAP 2022 conference abstract: Explainability has become an important topic both in Data Science and AI in general and in recommender systems in particular, as algorithms have become much less inherently explainable. However, explainability has different interpretations and goals in different fields. For example, interpretability and explanainability tools in machine learning are predominantly developed for Data Scientists to understand and scrutinize their models. Current tools are therefore often quite technical and not very ‘user-friendly’. I will illustrate this with our recent work on improving the explainability of model-agnostic tools such as LIME and SHAP. Another stream of research on explainability in the HCI and XAI fields focuses more on users’ needs for explainability, such as contrastive and selective explanations and explanations that fit with the mental models and beliefs of the user. However, how to satisfy those needs is still an open question. Based on recent work in interactive AI and machine learning, I will propose that explainability goes together with interactivity, and will illustrate this with examples from our own work in music genre exploration, that combines visualizations and interactive tools to help users understand and tune our exploration model. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/exuminvitedtalk-220705091145-12e6cd67-thumbnail.jpg?width=120&height=120&fit=bounds" /> invited talk in the ExUM workshop in the UMAP 2022 conference abstract: Explainability has become an important topic both in Data Science and AI in general and in recommender systems in particular, as algorithms have become much less inherently explainable. However, explainability has different interpretations and goals in different fields. For example, interpretability and explanainability tools in machine learning are predominantly developed for Data Scientists to understand and scrutinize their models. Current tools are therefore often quite technical and not very ‘user-friendly’. I will illustrate this with our recent work on improving the explainability of model-agnostic tools such as LIME and SHAP. Another stream of research on explainability in the HCI and XAI fields focuses more on users’ needs for explainability, such as contrastive and selective explanations and explanations that fit with the mental models and beliefs of the user. However, how to satisfy those needs is still an open question. Based on recent work in interactive AI and machine learning, I will propose that explainability goes together with interactivity, and will illustrate this with examples from our own work in music genre exploration, that combines visualizations and interactive tools to help users understand and tune our exploration model.

Explainability in AI and Recommender systems: let’s make it interactive! from Eindhoven University of Technology / JADS

]]> 218 0 https://cdn.slidesharecdn.com/ss_thumbnails/exuminvitedtalk-220705091145-12e6cd67-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Recommender systems to help people move forward /slideshow/recommender-systems-to-help-people-move-forward/119903274 recsysnl17okt2018-181018145230
My talk at the 11th RecSys NL meetup (Oct 17, 2018) in Utrecht about the research on user-centric recommender systems]]>
My talk at the 11th RecSys NL meetup (Oct 17, 2018) in Utrecht about the research on user-centric recommender systems]]> Thu, 18 Oct 2018 14:52:30 GMT /slideshow/recommender-systems-to-help-people-move-forward/119903274 MartijnWillemsen@slideshare.net(MartijnWillemsen) Recommender systems to help people move forward MartijnWillemsen My talk at the 11th RecSys NL meetup (Oct 17, 2018) in Utrecht about the research on user-centric recommender systems <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/recsysnl17okt2018-181018145230-thumbnail.jpg?width=120&height=120&fit=bounds" /> My talk at the 11th RecSys NL meetup (Oct 17, 2018) in Utrecht about the research on user-centric recommender systems

Recommender systems to help people move forward from Eindhoven University of Technology / JADS

]]> 120 1 https://cdn.slidesharecdn.com/ss_thumbnails/recsysnl17okt2018-181018145230-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 What recommender systems can learn from decision psychology about preference elicitation and behavioral change /slideshow/what-recommender-systems-can-learn-from-decision-psychology-about-preference-elicitation-and-behavioral-change/66063813 recsyspsyboiseumn2016-160915154214
�ݺ�ߣs of my talks at Boise State (Idaho) and Grouplens at University of Minnesota ]]>
�ݺ�ߣs of my talks at Boise State (Idaho) and Grouplens at University of Minnesota ]]> Thu, 15 Sep 2016 15:42:14 GMT /slideshow/what-recommender-systems-can-learn-from-decision-psychology-about-preference-elicitation-and-behavioral-change/66063813 MartijnWillemsen@slideshare.net(MartijnWillemsen) What recommender systems can learn from decision psychology about preference elicitation and behavioral change MartijnWillemsen �ݺ�ߣs of my talks at Boise State (Idaho) and Grouplens at University of Minnesota <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/recsyspsyboiseumn2016-160915154214-thumbnail.jpg?width=120&height=120&fit=bounds" /> �ݺ�ߣs of my talks at Boise State (Idaho) and Grouplens at University of Minnesota

What recommender systems can learn from decision psychology about preference elicitation and behavioral change from Eindhoven University of Technology / JADS

]]> 961 6 https://cdn.slidesharecdn.com/ss_thumbnails/recsyspsyboiseumn2016-160915154214-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 SSIi2016 keynote Martijn Willemsen /slideshow/ssi2016-keynote-martijn-willemsen/63643295 ssi2016keynotewillemsen-160701122953
title: Combining process data and subjective data to better understand online behavior presented at the 3rd Social Sciences and the Internet conference, Eindhoven, July 1 2016 http://ssi.ieis.tue.nl/]]>
title: Combining process data and subjective data to better understand online behavior presented at the 3rd Social Sciences and the Internet conference, Eindhoven, July 1 2016 http://ssi.ieis.tue.nl/]]> Fri, 01 Jul 2016 12:29:53 GMT /slideshow/ssi2016-keynote-martijn-willemsen/63643295 MartijnWillemsen@slideshare.net(MartijnWillemsen) SSIi2016 keynote Martijn Willemsen MartijnWillemsen title: Combining process data and subjective data to better understand online behavior presented at the 3rd Social Sciences and the Internet conference, Eindhoven, July 1 2016 http://ssi.ieis.tue.nl/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ssi2016keynotewillemsen-160701122953-thumbnail.jpg?width=120&height=120&fit=bounds" /> title: Combining process data and subjective data to better understand online behavior presented at the 3rd Social Sciences and the Internet conference, Eindhoven, July 1 2016 http://ssi.ieis.tue.nl/

SSIi2016 keynote Martijn Willemsen from Eindhoven University of Technology / JADS

]]> 532 6 https://cdn.slidesharecdn.com/ss_thumbnails/ssi2016keynotewillemsen-160701122953-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Improving user experience in recommender systems /slideshow/improving-user-experience-in-recommender-systems/54695825 talkgraz-151103162318-lva1-app6891
How latent feature diversification can decrease choice difficulty and improve choice satisfaction Talk at Graz University of Technology - Nov 3, 2015]]>
How latent feature diversification can decrease choice difficulty and improve choice satisfaction Talk at Graz University of Technology - Nov 3, 2015]]> Tue, 03 Nov 2015 16:23:18 GMT /slideshow/improving-user-experience-in-recommender-systems/54695825 MartijnWillemsen@slideshare.net(MartijnWillemsen) Improving user experience in recommender systems MartijnWillemsen How latent feature diversification can decrease choice difficulty and improve choice satisfaction Talk at Graz University of Technology - Nov 3, 2015 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/talkgraz-151103162318-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds" /> How latent feature diversification can decrease choice difficulty and improve choice satisfaction Talk at Graz University of Technology - Nov 3, 2015

Improving user experience in recommender systems from Eindhoven University of Technology / JADS

]]> 1610 7 https://cdn.slidesharecdn.com/ss_thumbnails/talkgraz-151103162318-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-MartijnWillemsen-48x48.jpg?cb=1723131114 Associate professor with over 15 years of teaching experience in Decision making, consumer behavior and cognition and recommender systems. Dedicated research experience in both applied and basic topics, highly skilled in experimental design, statistics. process data analysis. www.maritjnwillemsen.nl https://cdn.slidesharecdn.com/ss_thumbnails/exuminvitedtalk-220705091145-12e6cd67-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/explainability-in-ai-and-recommender-systems-lets-make-it-interactive/252124352 Explainability in AI... https://cdn.slidesharecdn.com/ss_thumbnails/recsysnl17okt2018-181018145230-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/recommender-systems-to-help-people-move-forward/119903274 Recommender systems to... https://cdn.slidesharecdn.com/ss_thumbnails/recsyspsyboiseumn2016-160915154214-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/what-recommender-systems-can-learn-from-decision-psychology-about-preference-elicitation-and-behavioral-change/66063813 What recommender syste...