Measures & Metrics
Collection of SOTA ML quality assurance methods like bias, generalizations, robustness, uncertainty, and so forth about use cases and regulatory topics.
Scope
Since 2020, the Measures & Metrics workstream has researched regulatory aspects inside of Machine Learning for Health. We study a collection of SOTA ML quality assurance methods like bias, generalizations, robustness, uncertainty, and so forth about use cases and regulatory topics. Our expectation is finish the project until the end of 2022.
Today, our multidisciplinary team has students and professionals from different companies, laboratories, universities worldwide focusing on creating regulatory documents and providing better solutions to society.
We already developed a paper about Machine Learning for Health Audit in this workstream (see in publications). Our objective is to move to easy to maintain and use web resources.
Aims
Develop better regulations by publications, international standards about measures, and metrics inside Machine Learning for Health.
Outputs
Collaboration resources
You are welcome to inquire about the work stream and opporunities for collaboration directly with the work stream team.
- General contact Luis Oala, luis@aiaudit.org
Meetings
Regular meetings for this work stream take place at the below coordinates.
- Meetings Weekly, Thursday, 2:00 PM, CET
- Zoom room Click here to join meeting
Communication
You can subsbscribe to the work stream mailing list to receive updates and join the asynchronous group chat.
- Group chat
- Mailing list
Tools
We use different tools in our remote work. They include shared documents, github projects for code as well as task tracking and a collaborative whiteboard for ideation. You can request access via the below links.
- Shared drive
- Github project
- Collaborative whiteboard
You can find more information about the way we usually carry out our work remotely in teams here.
Milestones
Important reference material
This is a list of related work and resources relevant for this work stream. It comprises resources the work stream contributors consider good practice.