Hardware-efficient tractable probabilistic inference for TinyML Neurosymbolic AI applications

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

6

Series

2025 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2025

Abstract

Neurosymbolic AI (NSAI) has recently emerged to mitigate limitations associated with deep learning (DL) models, e.g. quantifying their uncertainty or reason with explicit rules. Hence, TinyML hardware will need to support these symbolic models to bring NSAI to embedded scenarios. Yet, although symbolic models are typically compact, their sparsity and computation resolution contrasts with low-resolution and dense neuro models, which is a challenge on resource-constrained TinyML hardware severely limiting the size of symbolic models that can be computed. In this work, we remove this bottleneck leveraging a tight hardware/software integration to present a complete framework to compute NSAI with TinyML hardware. We focus on symbolic models realized with tractable probabilistic circuits (PCs), a popular subclass of probabilistic models for hardware integration. This framework: (1) trains a specific class of hardware-efficient deterministic PCs, chosen for the symbolic task; (2) compresses this PC until it can be computed on TinyML hardware with minimal accuracy degradation, using our nth-root compression technique, and (3) deploys the complete NSAI model on TinyML hardware. Compared to a 64b precision baseline necessary for the PC without compression, our workflow leads to significant hardware reduction on FPGA (up to 82.3% in FF, 52.6% in LUTs, and 18.0% in Flash usage) and an average inference speedup of 4.67× on ESP32 microcontroller.

Description

Publisher Copyright: © 2025 IEEE. | openaire: EC/HE/101071179/EU//SUSTAIN

Keywords

Other note

Citation

Leslin, J, Trapp, M & Andraud, M 2025, Hardware-efficient tractable probabilistic inference for TinyML Neurosymbolic AI applications. in 2025 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2025. IEEE, International Conference on Omni-Layer Intelligent Systems, Madison, Wisconsin, United States, 04/08/2025. https://doi.org/10.1109/COINS65080.2025.11125733