2 Hits in 6.9 sec

VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition [article]

Randy Ardywibowo, Shahin Boluki, Zhangyang Wang, Bobak Mortazavi, Shuai Huang, Xiaoning Qian
2022 arXiv   pre-print
To tackle FDS, this paper proposes a Bayesian learning framework of Variational Foresight Dynamic Selection (VFDS).  ...  We apply VFDS on the Human Activity Recognition (HAR) task where the performance-cost trade-off is critical in its practice.  ...  Qian has been supported in part by the National Science Foundation (NSF) Awards 1553281, 1812641, 1835690, 1934904, and 2119103.  ... 
arXiv:2204.00130v1 fatcat:hxbkpr33ojdhtakfscefoqkih4

VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty

Randy Ardywibowo, Zepeng Huo, Zhangyang Wang, Bobak J. Mortazavi, Shuai Huang, Xiaoning Qian
2022 International Conference on Machine Learning  
By interpreting dynamically growing neural networks as a Bayesian approximation, and defining flexible implicit variational distributions, VariGrow detects if a new task is arriving through an energy-based  ...  This paper proposes a variational architecture growing framework dubbed VariGrow.  ...  Acknowledgments This project is supported in part by the Defense Advanced Research Projects Agency (DARPA) under grant FA8750-18-2-0027. X.  ... 
dblp:conf/icml/ArdywibowoHWMHQ22 fatcat:rb3gq3zxe5gd7oq7jlsdmoit2e