Explore federated learning and integration techniques for biomedical data in this informative lecture presented by Dr. Jose-Luis Ambite from USC Information Sciences Institute. Discover how hospitals, clinics, and researchers can collaborate on machine learning projects while maintaining data privacy and complying with regulations. Learn about the FLINT architecture, which combines federated learning with data integration methods to address challenges in distributed biomedical data analysis. Gain insights into encrypted model training, gradient noise protection, and the importance of data harmonization and imputation in neuroimaging tasks. Understand the speaker's expertise in data integration, databases, semantic web, and biomedical data science as you delve into this cutting-edge approach to collaborative medical research.
Federated Learning and Integration of Biomedical Data
USC Information Sciences Institute via YouTube
Overview
Syllabus
Federated Learning and Integration of Biomedical Data
Taught by
USC Information Sciences Institute
Related Courses
-
Federated Learning and Privacy-preserving RAGs
-
Learning and Unlearning Your Data in Federated Settings
-
Federated Learning - Unlocking the Value of Discrete Data for Enterprise
-
Preserving Data Privacy in Federated Learning - Xiaokui Xiao
4.0 -
Gradient Obfuscation Gives a False Sense of Security in Federated Learning
-
Federated Learning - Machine Learning on Decentralized Data
5.0
