J
Josh Andres
Researcher at IBM
Publications - 51
Citations - 652
Josh Andres is an academic researcher from IBM. The author has contributed to research in topics: Computer science & Interaction design. The author has an hindex of 10, co-authored 39 publications receiving 279 citations. Previous affiliations of Josh Andres include RMIT University & Monash University.
Papers
More filters
Proceedings ArticleDOI
AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinates
Daniel Karl I. Weidele,Justin D. Weisz,Erick Oduor,Michael Muller,Josh Andres,Alexander G. Gray,Dakuo Wang +6 more
TL;DR: A first user evaluation by 10 data scientists of an experimental system, AutoAIViz, that aims to visualize AutoAI's model generation process finds that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.
Proceedings ArticleDOI
Designing Ground Truth and the Social Life of Labels
Michael Muller,Christine T. Wolf,Josh Andres,Michael Desmond,Narendra Nath Joshi,Zahra Ashktorab,Aabhas Sharma,Kristina Brimijoin,Qian Pan,Evelyn Duesterwald,Casey Dugan +10 more
TL;DR: The authors provide a grounded account of the work of labeling teams with domain experts, including the experiences of labeling, collaborative configurations and work-practices, and quality issues, and show three major patterns in the social design of ground truth data: principled design, iterative design and improvisational design.
Proceedings ArticleDOI
AutoDS: Towards Human-Centered Automation of Data Science
TL;DR: In this paper, an automated machine learning (AutoML) system that aims to leverage the latest ML automation techniques to support data science projects is introduced. But the system is limited to a single dataset and the user does not have access to the entire dataset.
Proceedings ArticleDOI
AutoDS: Towards Human-Centered Automation of Data Science
TL;DR: In this article, an automated machine learning (AutoML) system that aims to leverage the latest ML automation techniques to support data science projects is presented. But, the system only needs data workers to upload their dataset, then the system can automatically suggest ML configurations, preprocess data, select algorithm, and train the model.
Proceedings ArticleDOI
Introducing Peripheral Awareness as a Neurological State for Human-computer Integration
Josh Andres,mc schraefel,Nathan Semertzidis,Brahmi Dwivedi,Yutika Chandrashekhar Kulwe,Juerg von Kaenel,Florian 'Floyd' Mueller +6 more
TL;DR: This work presents "Ena", a novel EEG-eBike system that draws from the user's neural activity to determine when the user is in a state of peripheral awareness to regulate engine support, and suggests that Ena suggests that the work facilitates a safe and enjoyable human-computer integration experience.