A comparative study of preprocessing and model compression techniques in deep learning for forest sound classification
Deep-learning models play a significant role in modern software solutions, with the
capabilities of handling complex tasks, improving accuracy, automating processes, and …
capabilities of handling complex tasks, improving accuracy, automating processes, and …
[HTML][HTML] DNNShifter: An efficient DNN pruning system for edge computing
Deep neural networks (DNNs) underpin many machine learning applications. Production
quality DNN models achieve high inference accuracy by training millions of DNN …
quality DNN models achieve high inference accuracy by training millions of DNN …
Symmetry-structured convolutional neural networks
We consider convolutional neural networks (CNNs) with 2D structured features that are
symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships …
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
Network Intrusion Detection Systems (NIDS) play a crucial role in ensuring cybersecurity
across various digital infrastructures. However, traditional NIDS face significant challenges …
across various digital infrastructures. However, traditional NIDS face significant challenges …
Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning
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 …
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 …
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 …
client resources and the problem of stragglers caused by high heterogeneity. Despite efforts …
Peeking inside Sparse Neural Networks using Multi-Partite Graph Representations
Abstract Modern Deep Neural Networks (DNNs) have achieved very high performance at
the expense of computational resources. To decrease the computational burden, several …
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 …
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
Vehicular Edge computing requires computational power from connected Edge devices in
the network to process incoming vehicle work requests. This connection and offloading …
the network to process incoming vehicle work requests. This connection and offloading …