Understanding machine-learning models, especially in the biomedical sciences, has gained prominence due to concerns about AI’s fairness and reliability. This emphasis has been underscored by a surge in explainable AI (XAI) research during the COVID-19 pandemic, with a notable peak in publications in October 2020. Although a universal definition of explainability in AI is still out of reach, there’s a commendable shift towards improving the robustness and reliability of applied machine learning in the field.
You can learn more in the new published article of Institute for anthropological research : https://www.cell.com/patterns/pdf/S2666-3899(23)00199-X.pdf
