Suchergebnisse - ML: Learning on the Edge & Model Compression

A comprehensive review of model compression techniques in machine learning von Dantas, Pierre Vilar, Sabino da Silva, Waldir, Cordeiro, Lucas Carvalho, Carvalho, Celso Barbosa

“… This paper critically examines model compression techniques within the machine learning (ML …”
Volltext

A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques von Li, Wenbin, Hacid, Hakim, Almazrouei, Ebtesam, Debbah, Merouane

“… and adapted in technologies such as data processing, model compression, distributed inference, and advanced learning paradigms for Edge ML requirements …”
Volltext

FedComp: A Federated Learning Compression Framework for Resource-Constrained Edge Computing Devices von Wu, Donglei, Yang, Weihao, Jin, Haoyu, Zou, Xiangyu, Xia, Wen, Fang, Binxing

“… Top-K sparsification-based compression techniques are popular and powerful for reducing communication costs in federated learning (FL …”
Volltext

Machine Learning for Microcontroller-Class Hardware - A Review von Saha, Swapnil Sayan, Sandha, Sandeep Singh, Srivastava, Mani

“… We characterize a closed-loop widely applicable workflow of machine learning model development for microcontroller class devices and show that several classes of applications adopt a specific instance …”
Volltext

Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review von Shuvo, Md. Maruf Hossain, Islam, Syed Kamrul, Cheng, Jianlin, Morshed, Bashir I.

“… However, deploying these highly accurate models for data-driven, learned, automatic, and practical machine learning (ML …”
Volltext

Power Efficient Machine Learning Models Deployment on Edge IoT Devices von Fanariotis, Anastasios, Orphanoudakis, Theofanis, Kotrotsios, Konstantinos, Fotopoulos, Vassilis, Keramidas, George, Karkazis, Panagiotis

“… This change has been achieved by incorporating small embedded devices into a larger computational system, connected through networking and referred to as edge devices …”
Volltext

Communication-Efficient Federated Learning for Wireless Edge Intelligence in IoT von Mills, Jed, Hu, Jia, Min, Geyong

“… The rapidly expanding number of Internet of Things (IoT) devices is generating huge quantities of data, but public concern over data privacy means users are apprehensive to send data to a central server for machine learning (ML) purposes …”
Volltext

When Climate Meets Machine Learning: Edge to Cloud ML Energy Efficiency von Marculescu, Diana

“… A large portion of current cloud and edge workloads feature Machine Learning (ML) tasks, thereby requiring a deep understanding of their energy efficiency …”
Volltext

Privacy-Preserving Federated Learning With Resource-Adaptive Compression for Edge Devices von Hidayat, Muhammad Ayat, Nakamura, Yugo, Arakawa, Yutaka

“… Federated learning (FL) has gained widespread attention as a distributed machine learning (ML …”
Volltext

Towards edge computing in intelligent manufacturing: Past, present and future von Nain, Garima, Pattanaik, K.K., Sharma, G.K.

“… It drives the convergence of several cutting-edge technologies to provoke autonomous, fully integrated, collaborated, highly automated, and customized industries. Edge Computing (EC …”
Volltext

Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices von Mnif, Mahdi, Sahnoun, Salwa, Ben Saad, Yasmine, Fakhfakh, Ahmed, Kanoun, Olfa

“… Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices …”
Volltext

Efficient Resource-Constrained Federated Learning Clustering with Local Data Compression on the Edge-to-Cloud Continuum von Prigent, Cedric, Chelli, Melvin, Costan, Alexandru, Cudennec, Loic, Schubotz, Rene, Antoniu, Gabriel

“… While it can be a highly efficient tool for large-scale collaborative training of Machine Learning (ML …”
Volltext

Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics von Amaizu, Maryleen Uluaku, Ali, Muhammad, Anjum, Ashiq, Liu, Lu, Liotta, Antonio, Rana, Omer

“… However, Machine Learning (ML) algorithms typically require significant computational resources, hence cannot be directly deployed on resource-constrained edge devices for learning and analytics …”
Volltext

Tuning DNN Model Compression to Resource and Data Availability in Cooperative Training von Malandrino, Francesco, di Giacomo, Giuseppe, Karamzade, Armin, Levorato, Marco, Chiasserini, Carla Fabiana

“… Model compression is a fundamental tool to execute machine learning (ML) tasks on the diverse set of devices populating current-and next-generation networks, thereby exploiting their resources and data …”
Volltext

TinyML model compression: A comparative study of pruning and quantization on selected standard and custom neural networks von Shabir, Muhammad Yasir, Torta, Gianluca, Damiani, Ferruccio

“… In Machine Learning (ML), the deployment of complex Neural Network (NN) models on memory-constrained Internet of Things (IoT …”
Volltext

PPEFL: An Edge Federated Learning Architecture with Privacy-Preserving Mechanism von Liu, Zhenpeng, Gao, Zilin, Wang, Jingyi, Liu, Qiannan, Wei, Jianhang

“… The emergence of federal learning makes up for some shortcomings of machine learning, and its distributed machine learning paradigm can effectively solve the problem of data islands, allowing users …”
Volltext

Joint Video Frame Scheduling and Resource Allocation for Device-Edge Collaborative Video Intelligent Analytics von Li, Jiayi, Chi, Xiaoyu, Wang, Hui, Su, Yi, Han, Shujun, Xu, Xiaodong

“… Specifically, we propose a joint optimization scheme for video frame scheduling, adaptive video frame compression and Machine Learning (ML …”
Volltext

HiRISE: High-Resolution Image Scaling for Edge ML via In-Sensor Compression and Selective ROI von Reidy, Brendan, Tabrizchi, Sepehr, Mohammadi, Mohamadreza, Angizi, Shaahin, Roohi, Arman, Zand, Ramtin

“… With the rise of tiny IoT devices powered by machine learning (ML), many researchers have directed their focus toward compressing models to fit on tiny edge devices …”
Volltext

Performance Benchmarking of ML Models for Resource Constrained Devices von S, Sreeraj, D, Harikrishnan

“… This study underscores the importance of model compression and optimization techniques to enable the deployment of sophisticated models in resource constrained devices …”
Volltext

Compressing and Fine-tuning DNNs for Efficient Inference in Mobile Device-Edge Continuum von Singh, Gurtaj, Chukhno, Olga, Campolo, Claudia, Molinaro, Antonella, Chiasserini, Carla Fabiana

“… (hence, model complexity) and latency and energy consumption. In this work, we explore the different options for the deployment of a machine learning pipeline …”
Volltext