Date(s) - 10 Dec 2018
4:00 pm - 5:00 pm
Data Quality is at the heart of AI/ML and is one of the key challenges we face in Life Sciences to make AI a success.
In this panel we will discuss how to address these data quality issues and what steps we need to take to improve things in the future.
We will also look at practical ways to improve things now.
Please submit your questions now for the panellists
- Panel members include:
- Terry Stouch, Science for Solutions
- Isabella Feierberg, AstraZeneca
- Jamie Powers, Cambridge Semantics
- Sirarat Sarntivijai, ELIXIR EU
- Jabe Wilson, Elsevier
- Some opening questions for our panelists could be:
- Define “data quality” – FAIR? Open? Shareable? What are metrics for FAIR-ness of data? How accurate are metadata?
- Discuss metadata standards, as-is and to-be
- How high level of quality is needed at specific points of research work cycle?
- Various models in AI are more or less sensitive to outliers, missing values, etc