- Federated learning infrastructure
- Privacy health research for both cloud and edge learning
Use cases with applications for:
- Distributed mobile-based A.I. training for images
- Edge computing for DNA information
- Edge computing for immunovigilance using unique health signatures
- Federated cloud learning on real-world data
A group of federated learning engineers at doc.ai will present during this webinar then answer direct questions from the audience.
Our team at doc.ai, a Palo Alto-based deep learning company, has made significant advances in federated learning and other privacy-preserving techniques in healthcare applications to build intelligent systems without moving data.
Federated learning provides an inroad to sharing machine learning models without sharing the underlying data used to train these models. The technique helps us learn from privacy-sensitive data on edge devices.
Our first work in federated learning was presented last December at the Neurips conference by Philip Dow, head of mobile federated learning at doc.ai.