Search Results for author:
Found 6 papers, 1 papers with code
Can Calibration Improve Sample Prioritization?
Calibration can reduce overconfident predictions of deep neural networks, but can calibration also accelerate training?
Zero-Shot Federated Learning with New Classes for Audio Classification
Federated learning is an effective way of extracting insights from different user devices while preserving the privacy of users.
Federated Learning with Heterogeneous Labels and Models for Mobile Activity Monitoring
Such applications demand characterization of insights from multiple resource-constrained user devices using machine learning techniques for effective personalized activity monitoring.
Bayesian Active Learning for Wearable Stress and Affect Detection
In the recent past, psychological stress has been increasingly observed in humans, and early detection is crucial to prevent health risks.
Resource-Constrained Federated Learning with Heterogeneous Labels and Models
In addition, in this paper we explore a new challenge of interest -- to handle label heterogeneities in federated learning.
ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition
Various health-care applications such as assisted living, fall detection etc., require modeling of user behavior through Human Activity Recognition (HAR).
