Generating Neural Networks for Diverse Networking Classification Tasks via Hardware-Aware Neural Architecture Search

G Xie, Q Li, Z Shi, H Fang, S Ji, Y Jiang… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Neural networks (NNs) are widely used in classification-based networking analysis to help
traffic transmission and system security. However, there are heterogeneous network devices …

Building high-throughput neural architecture search workflows via a decoupled fitness prediction engine

AK Rorabaugh, S Caino-Lores… - … on Parallel and …, 2022 - ieeexplore.ieee.org
Neural networks (NN) are used in high-performance computing and high-throughput
analysis to extract knowledge from datasets. Neural architecture search (NAS) automates …

{LitePred}: Transferable and Scalable Latency Prediction for {Hardware-Aware} Neural Architecture Search

C Feng, LL Zhang, Y Liu, J Xu, C Zhang… - … USENIX Symposium on …, 2024 - usenix.org
Hardware-Aware Neural Architecture Search (NAS) has demonstrated success in
automating the design of affordable deep neural networks (DNNs) for edge platforms by …

FLASH: F ast Neura l A rchitecture S earch with H ardware Optimization

G Li, SK Mandal, UY Ogras, R Marculescu - ACM Transactions on …, 2021 - dl.acm.org
Neural architecture search (NAS) is a promising technique to design efficient and high-
performance deep neural networks (DNNs). As the performance requirements of ML …

A Generic Graph-Based Neural Architecture Encoding Scheme With Multifaceted Information

X Ning, Y Zheng, Z Zhou, T Zhao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Neural architecture search (NAS) can automatically discover well-performing architectures
in a large search space and has been shown to bring improvements to various applications …

[HTML][HTML] Network intrusion detection based on an efficient neural architecture search

R Lyu, M He, Y Zhang, L Jin, X Wang - Symmetry, 2021 - mdpi.com
Deep learning has been applied in the field of network intrusion detection and has yielded
good results. In malicious network traffic classification tasks, many studies have achieved …

CHaNAS: coordinated search for network architecture and scheduling policy

W Chen, Y Wang, G Lin, C Gao, C Liu… - Proceedings of the 22nd …, 2021 - dl.acm.org
Automatically design an efficient DNN solution for a given deep learning task on the target
hardware mainly decided by the neural network architecture and the schedule mapping …

Evolution of hardware-aware neural architecture search (NAS) on the edge

B Richey, M Clay, C Grecos… - Real-Time Image …, 2023 - spiedigitallibrary.org
Neural Architecture Search (NAS) is a method of autonomously designing deep learning
models to achieve top performance for tasks such as data classification and data retrieval by …

What to expect of hardware metric predictors in NAS

KA Laube, M Mutschler, A Zell - International Conference on …, 2022 - proceedings.mlr.press
Abstract Modern Neural Architecture Search (NAS) focuses on finding the best performing
architectures in hardware-aware settings; eg, those with an optimal tradeoff of accuracy and …

Search-Time Efficient Device Constraints-Aware Neural Architecture Search

O Dutta, T Kanvar, S Agarwal - International Conference on Pattern …, 2023 - Springer
Edge computing aims to enable edge devices, such as IoT devices, to process data locally
instead of relying on the cloud. However, deep learning techniques like computer vision and …