Webinar, USACM, TTA-Uncertainty Quantification and Probabilistic Modeling:: Title: Measuring dataset similarity in clustering-based, uncertainty-aware federated learning. Speaker: Prof. Chao Hu, University of Connecticut

This is a reminder that our next monthly webinar is December 5, 3-4pm EST. The speaker will be Associate Professor Chao Hu from University of Connecticut. We are hoping the format will promote a lively interactive discussion and engage both junior and senior members of our community. Look forward to seeing you there.

Monthly Webinar by USACM, TTA-Uncertainty Quantification and Probabilistic Modeling

December 5; 3pm EST

Speaker: Associate Professor Chao Hu, University of Connecticut

Title: Measuring dataset similarity in clustering-based, uncertainty-aware federated learning

Federated learning has emerged as a privacy-preserving, decentralized strategy that allows multiple clients to train machine learning models collaboratively without sharing data. This strategy has great potential to tackle critical data privacy and security challenges in machine health monitoring, particularly when there is a need to train fault classification models using distributed datasets across industrial clients. This talk will provide an overview of clustering-based federated learning and how it can benefit from quantifying the predictive uncertainty of trained machine learning models. A central emphasis will be placed on uncertainty-aware federated learning to address data heterogeneity in fleets of machine components. The solution methodology will center around measuring dataset similarity while ensuring data privacy.

Join Zoom Meeting
https://us06web.zoom.us/j/92756548524?pwd=cTFoRXIvNVN4dVFoaHEzK0pQQjhldz09 (Meeting ID: 927 5654 8524/Passcode: 934745)

Please forward to anyone who may be interested.