Work

Fast-Inf: Ultra-Fast Embedded Intelligence on the Batteryless Edge

Year: 2024

Type: conference-paper

Abstract: Batteryless edge devices are extremely resource-constrained compared to traditional mobile platforms. Existing tiny deep neural network (DNN) inference solutions are problematic due to their slow and resource-intensive nature, rendering them unsuitable for batteryless edge devices. To address this problem, we propose a new approach to embedded intelligence, called Fast-Inf, which achieves extremely lightweight computation and minimal latency. Fast-Inf uses binary tree-based neural networks that are ultra-fast and energy-efficient due to their logarithmic time complexity. Additionally, Fast-Inf models can skip the leaf nodes when necessary, further minimizing latency without requiring any modifications to the model or retraining. Moreover, Fast-Inf models have significantly lower backup and runtime memory overhead. Our experiments on an MSP430FR5994 platform showed that Fast-Inf can achieve ultra-fast and energy-efficient inference (up to 700x speedup and reduced energy) compared to a conventional DNN.

Source: ACM Conference on Embedded Networked Sensor Systems (SenSys)

DOI: 10.1145/3666025.3699335

Authors: Leonardo Lucio Custode, Pietro Farina, Eren Yildiz, Renan Beran Kilic, Kasim Sinan Yildirim, Giovanni Iacca

Institutions: University of Trento, Ege University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: hybrid

Funder: European Commission