Researchers propose a hardware-software codesign using FDSOI ferroelectric FETs to accelerate probabilistic tree inference on edge devices. The work explores how ferroelectric transistor properties enable efficient execution of tree-based ML models with reduced power consumption.
Infrastructure
Probabilistic Tree Inference Enabled by FDSOI Ferroelectric FETs
FDSOI ferroelectric FETs accelerate probabilistic tree inference on edge devices with dramatically reduced power consumption, enabling practical battery-constrained ML execution.
Wednesday, April 8, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
infrastructure