An example of a federated learning application is collaborative health data analysis, where multiple healthcare institutions collaborate to train machine learning models without sharing sensitive patient data. Each institution has its own data set, but they contribute to a shared model by computing updates locally and sending them to a central server for aggregation. This approach allows for insights into patient outcomes while preserving privacy policies and regulations. Federated learning enhances data security and ensures compliance, enabling organizations to leverage AI technologies collaboratively without compromising on privacy.