Low-Overhead Early-Stopping Policies for Efficient Random Forests Inference on Microcontrollers - VLSI-SoC: Technology Advancement on SoC Design Access content directly
Conference Papers Year : 2022

Low-Overhead Early-Stopping Policies for Efficient Random Forests Inference on Microcontrollers

Abstract

Random Forests (RFs) are popular Machine Learning models for edge computing, due to their lightweight nature and high accuracy on several common tasks. Large RFs however, still have significant energy costs, a serious concern for battery-operated ultra-low-power devices. Following the adaptive (or dynamic) inference paradigm, we introduce a hardware-friendly early stopping policy for RF-based classifiers, halting the execution as soon as a sufficient prediction confidence is achieved. We benchmark our approach on three state-of-the-art datasets relative to different embedded classification tasks, and deploy our models on a single core RISC-V microcontroller. We achieve an energy reduction ranging from 18% to more than 91%, with an accuracy drop lower than 0.5%. Additionally, we compare our approach with other early-stopping policies, showing that we outperform them.
Embargoed file
Embargoed file
0 7 11
Year Month Jours
Avant la publication
Wednesday, January 1, 2025
Embargoed file
Wednesday, January 1, 2025
Please log in to request access to the document

Dates and versions

hal-04419563 , version 1 (26-01-2024)

Licence

Attribution

Identifiers

Cite

Francesco Daghero, Alessio Burrello, Chen Xie, Luca Benini, Andrea Calimera, et al.. Low-Overhead Early-Stopping Policies for Efficient Random Forests Inference on Microcontrollers. 29th IFIP/IEEE International Conference on Very Large Scale Integration - System on a Chip (VLSI-SoC), Oct 2021, Singapore, Singapore. pp.25-47, ⟨10.1007/978-3-031-16818-5_2⟩. ⟨hal-04419563⟩
25 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More