Library-Abstract-UNITED SOCIETIES OF SCIENCE

Home / USS Digital Library / Article / Details

Deployment of TinyML on THEJAS32 based IoT Platform

Publisher: IEEE

Authors: Vinod Aleena, Centre for Development of Advanced Computing N Prem Krishnan, Centre for Development of Advanced Computing R M Shibu, Centre for Development of Advanced Computing Gafoor A Subina, Centre for Development of Advanced Computing V S Bhagyasree, Centre for Development of Advanced Computing

Favorite
Share:

Abstract:

THEJAS32 SoC is based on the VEGA ET1031 processor, a 32-bit single core, in-order, 3-stage pipeline processor developed by C-DAC under the MDP. This work presents the maiden attempt to deploy Tiny Machine Learning (TinyML) on a hardware platform built around the THEJAS32 SoC. A TinyML model was trained and optimized using the TensorFlow framework using Google Colab and deployed to the hardware using the VEGA Software Development Kit (SDK). The model was compressed by as much as 97% compared to the one developed using TensorFlow. This validates the viability of the TinyML-IoT-THEJAS32 platform for TinyML applications.

Keywords: TinyML,RISC-V,Edge AI,THEJAS32,VEGA SDK

Published in: 2024 Asian Conference on Communication and Networks (ASIANComNet)

Date of Publication: --

DOI: -

Publisher: IEEE

ABSTRACT LIBRARY

Deployment of TinyML on THEJAS32 based IoT Platform

Publisher: IEEE

Abstract:

USS WeChat Official Account