MTLiquid: Enabling Efficient Multi-Task Learning using Liquid Neural Networks for Lightweight Healthcare Monitoring Systems
Experimental results for mortality prediction and sepsis early detection tasks for ICU patients show that, MTLiquid achieves strong performance comparable to the state-of-the-art single-task learning in both continuous-time networks and discrete-time networks.
Rachmad Vidya Wicaksana Putra, Fahad Abdul Rauf, M. Shafique
· 0 citations