Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT
Motivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current “smart everything” scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specif...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/1911 |
| _version_ | 1797618302756847616 |
|---|---|
| author | Ivan Rodriguez-Conde Celso Campos Florentino Fdez-Riverola |
| author_facet | Ivan Rodriguez-Conde Celso Campos Florentino Fdez-Riverola |
| author_sort | Ivan Rodriguez-Conde |
| collection | DOAJ |
| description | Motivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current “smart everything” scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specific mechanisms for enabling a collaborative inference across edge devices towards the in situ execution of highly complex state-of-the-art deep neural networks (DNNs), despite the resource-constrained nature of such infrastructures. In particular, the review discusses the most salient approaches conceived along those lines, elaborating on the specificities of the partitioning schemes and the parallelism paradigms explored, providing an organized and schematic discussion of the underlying workflows and associated communication patterns, as well as the architectural aspects of the DNNs that have driven the design of such techniques, while also highlighting both the primary challenges encountered at the design and operational levels and the specific adjustments or enhancements explored in response to them. |
| first_indexed | 2024-03-11T08:11:11Z |
| format | Article |
| id | doaj.art-c0d7c53dbd1b4e5abdef1bcf2847922d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:11:11Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c0d7c53dbd1b4e5abdef1bcf2847922d2023-11-16T23:07:47ZengMDPI AGSensors1424-82202023-02-01234191110.3390/s23041911Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoTIvan Rodriguez-Conde0Celso Campos1Florentino Fdez-Riverola2Department of Computer Science, University of Arkansas at Little Rock, 2801 South University Avenue, Little Rock, AR 72204, USADepartment of Computer Science, ESEI—Escuela Superior de Ingeniería Informática, Universidade de Vigo, 32004 Ourense, SpainCINBIO, Department of Computer Science, ESEI—Escuela Superior de Ingeniería Informática, Universidade de Vigo, 32004 Ourense, SpainMotivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current “smart everything” scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specific mechanisms for enabling a collaborative inference across edge devices towards the in situ execution of highly complex state-of-the-art deep neural networks (DNNs), despite the resource-constrained nature of such infrastructures. In particular, the review discusses the most salient approaches conceived along those lines, elaborating on the specificities of the partitioning schemes and the parallelism paradigms explored, providing an organized and schematic discussion of the underlying workflows and associated communication patterns, as well as the architectural aspects of the DNNs that have driven the design of such techniques, while also highlighting both the primary challenges encountered at the design and operational levels and the specific adjustments or enhancements explored in response to them.https://www.mdpi.com/1424-8220/23/4/1911IoTcollaborative inferencedeep neural networksdistributed computingDNN splittingtask offloading |
| spellingShingle | Ivan Rodriguez-Conde Celso Campos Florentino Fdez-Riverola Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT Sensors IoT collaborative inference deep neural networks distributed computing DNN splitting task offloading |
| title | Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT |
| title_full | Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT |
| title_fullStr | Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT |
| title_full_unstemmed | Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT |
| title_short | Horizontally Distributed Inference of Deep Neural Networks for AI-Enabled IoT |
| title_sort | horizontally distributed inference of deep neural networks for ai enabled iot |
| topic | IoT collaborative inference deep neural networks distributed computing DNN splitting task offloading |
| url | https://www.mdpi.com/1424-8220/23/4/1911 |
| work_keys_str_mv | AT ivanrodriguezconde horizontallydistributedinferenceofdeepneuralnetworksforaienablediot AT celsocampos horizontallydistributedinferenceofdeepneuralnetworksforaienablediot AT florentinofdezriverola horizontallydistributedinferenceofdeepneuralnetworksforaienablediot |