Model compression for deep neural networks: A survey

Z Li, H Li, L Meng - Computers, 2023 - mdpi.com
Currently, with the rapid development of deep learning, deep neural networks (DNNs) have
been widely applied in various computer vision tasks. However, in the pursuit of …

Lightweight neural architecture search for temporal convolutional networks at the edge

M Risso, A Burrello, F Conti, L Lamberti… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the
structure of Deep Learning (DL) models for complex tasks such as Image Classification or …

Q-ppg: Energy-efficient ppg-based heart rate monitoring on wearable devices

A Burrello, DJ Pagliari, M Risso… - … Circuits and Systems, 2021 - ieeexplore.ieee.org
Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost
photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) caused by …

Human activity recognition on microcontrollers with quantized and adaptive deep neural networks

F Daghero, A Burrello, C Xie, M Castellano… - ACM Transactions on …, 2022 - dl.acm.org
Human Activity Recognition (HAR) based on inertial data is an increasingly diffused task on
embedded devices, from smartphones to ultra low-power sensors. Due to the high …

Pruning techniques for artificial intelligence networks: a deeper look at their engineering design and bias: the first review of its kind

L Mohanty, A Kumar, V Mehta, M Agarwal… - Multimedia Tools and …, 2024 - Springer
Abstract Trained Artificial Intelligence (AI) models are challenging to install on edge devices
as they are low in memory and computational power. Pruned AI (PAI) models are therefore …

Toward Energy-efficient STT-MRAM-based Near Memory Computing Architecture for Embedded Systems

Y Li, X Wang, H Zhang, B Pan, K Qiu, W Kang… - ACM Transactions on …, 2024 - dl.acm.org
Convolutional Neural Networks (CNNs) have significantly impacted embedded system
applications across various domains. However, this exacerbates the real-time processing …

Multi-complexity-loss dnas for energy-efficient and memory-constrained deep neural networks

M Risso, A Burrello, L Benini, E Macii… - Proceedings of the …, 2022 - dl.acm.org
Neural Architecture Search (NAS) is increasingly popular to automatically explore the
accuracy versus computational complexity trade-off of Deep Learning (DL) architectures …

Privacy-preserving social distance monitoring on microcontrollers with low-resolution infrared sensors and cnns

C Xie, F Daghero, Y Chen, M Castellano… - … on Circuits and …, 2022 - ieeexplore.ieee.org
Low-resolution infrared (IR) array sensors offer a low-cost, low-power, and privacy-
preserving alternative to optical cameras and smartphones/wearables for social distance …

An Edge-side Real-time Video Analytics System with Dual Computing Resource Control

C Hu, R Lu, Q Sang, H Liang, D Wang… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Video analytics systems conduct video preprocessing to filter out unnecessary frames and
model inference using appropriately selected neural networks for high analytics speed …

RISC-V Processor Technologies for Aerospace Applications in the ISOLDE Project

W Fornaciari, F Reghenzani, G Agosta, D Zoni… - … on Embedded Computer …, 2023 - Springer
Modern space applications impose significant challenges to the design of hardware and
software platforms. Beyond traditional applications such as avionics, Attitude Orbit Control …