Synopsis
The Imageomics Institute is hosting a 3.5-day workshop to address the scarcity of ML-ready image and video datasets focused on addressing scientific questions. The event will bring together an interdisciplinary group around a shared interest of using AI/ML to extract scientific knowledge from image and video data, including ML researchers, domain scientists, information scientists, tool developers, and data curators. Participants will work in small groups to collaboratively curate or develop FAIR datasets, best practices, tools, infrastructure, and other products targeting the motivating challenge.
The event will take place August 14-17 at The Ohio State University in Columbus, OH. To apply to participate, please fill out the Image Datapalooza 2023 Application for Participation by the end of June 12, 2023. Funds to assist with travel expenses are available but limited, as is space. We expect to notify applicants about acceptance starting 10 days after the application due date.
About the event
Image Datapalooza 2023 will bring together an interdisciplinary group interested in using AI/ML to extract scientific knowledge from image and video data. We expect this to include AI/ML researchers, data scientists, domain scientists, data curators, tool developers, metadata researchers, and knowledge engineers. Participants will self-organize into small groups to work hands-on and collaboratively on self-selected targets and outcomes towards the motivations and goals of the event. The process of self-organizing and choosing work targets will be facilitated, but every participant will play an equally active role in making the event a successful, rewarding experience. We aim for an event that will give everyone ample opportunities to contribute their skills and experience, acquire new knowledge, increase technological awareness, and find potential new collaborators. Although the event is primarily designed to create work outcomes, the format will leave room for participant-driven exchange of know-how and skills.
Motivation
ML-ready datasets are in high demand but frequently scarce, and this presents an important obstacle to advancing ML algorithms for scientific research applications. What makes datasets ML-ready will ultimately depend on the specific application, but will usually include that they are easy to obtain, unencumbered for reuse, interoperable with applicable ML data standards, and structurally compliant with expectations for ML competition. For many research domains, such as biology, large amounts of potentially relevant data is available. However, the accessibility of these data is highly variable, and processing the data for ML or analyzing the functionality or suitability of a dataset for ML can be costly.