A comparative study of preprocessing and model compression techniques in deep learning for forest sound classification

T Paranayapa, P Ranasinghe, D Ranmal… - Sensors, 2024 - mdpi.com
Deep-learning models play a significant role in modern software solutions, with the
capabilities of handling complex tasks, improving accuracy, automating processes, and …

[HTML][HTML] DNNShifter: An efficient DNN pruning system for edge computing

BJ Eccles, P Rodgers, P Kilpatrick, I Spence… - Future Generation …, 2024 - Elsevier
Deep neural networks (DNNs) underpin many machine learning applications. Production
quality DNN models achieve high inference accuracy by training millions of DNN …

Symmetry-structured convolutional neural networks

KDG Maduranga, V Zadorozhnyy, Q Ye - Neural Computing and …, 2023 - Springer
We consider convolutional neural networks (CNNs) with 2D structured features that are
symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships …

Lightweight-Fed-NIDS: A Lightweight Federated Learning Framework for Enhanced Network Intrusion Detection System

A Bouayad, H Alami, MJ Idrissi, I Berrada - IEEE Access, 2024 - ieeexplore.ieee.org
Network Intrusion Detection Systems (NIDS) play a crucial role in ensuring cybersecurity
across various digital infrastructures. However, traditional NIDS face significant challenges …

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

S Racherla, P Sripathi, N Faruqui, MA Kabir… - IEEE …, 2024 - ieeexplore.ieee.org
The Internet of Things (IoT) represents a swiftly expanding sector that is pivotal in driving the
innovation of today's smart services. However, the inherent resource-constrained nature of …

Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization

BJ Eccles, L Wong, B Varghese - arXiv preprint arXiv:2404.16877, 2024 - arxiv.org
Edge machine learning (ML) enables localized processing of data on devices and is
underpinned by deep neural networks (DNNs). However, DNNs cannot be easily run on …

Data-free adaptive structured pruning for federated learning

W Fan, K Yang, Y Wang, C Chen, J Li - The Journal of Supercomputing, 2024 - Springer
Federated learning faces challenges in real-world deployment scenarios due to limited
client resources and the problem of stragglers caused by high heterogeneity. Despite efforts …

Peeking inside Sparse Neural Networks using Multi-Partite Graph Representations

E Cunegatti, D Bucur, G Iacca - 2023 - research.utwente.nl
Abstract Modern Deep Neural Networks (DNNs) have achieved very high performance at
the expense of computational resources. To decrease the computational burden, several …

Distilling What We Know

S Greengard - 2023 - dl.acm.org
ACM: Digital Library: Communications of the ACM ACM Digital Library Communications of the
ACM Volume 66, Number 9 (2023), Pages 15-17 News: Distilling What We Know Samuel …

Perception Workload Characterization and Prediction on the Edges with Memory Contention for Connected Autonomous Vehicles

S Tang, S Wang, S Fu, Q Yang - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Vehicular Edge computing requires computational power from connected Edge devices in
the network to process incoming vehicle work requests. This connection and offloading …