A review on TinyML: State-of-the-art and prospects
Machine learning has become an indispensable part of the existing technological domain. Edge computing and Internet of Things (IoT) together presents a new opportunity to imply machine learning techniques at the resource constrained embedded devices at the edge of the network. Conventional machine l...
| الحاوية / القاعدة: | Journal of King Saud University: Computer and Information Sciences |
|---|---|
| المؤلف الرئيسي: | |
| التنسيق: | مقال |
| اللغة: | الإنجليزية |
| منشور في: |
Springer
2022-04-01
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | http://www.sciencedirect.com/science/article/pii/S1319157821003335 |
| _version_ | 1848651254761259008 |
|---|---|
| author | Partha Pratim Ray |
| author_facet | Partha Pratim Ray |
| author_sort | Partha Pratim Ray |
| collection | DOAJ |
| container_title | Journal of King Saud University: Computer and Information Sciences |
| description | Machine learning has become an indispensable part of the existing technological domain. Edge computing and Internet of Things (IoT) together presents a new opportunity to imply machine learning techniques at the resource constrained embedded devices at the edge of the network. Conventional machine learning requires enormous amount of power to predict a scenario. Embedded machine learning – TinyML paradigm aims to shift such plethora from traditional high-end systems to low-end clients. Several challenges are paved while doing such transition such as, maintaining the accuracy of learning models, provide train-to-deploy facility in resource frugal tiny edge devices, optimizing processing capacity, and improving reliability. In this paper, we present an intuitive review about such possibilities for TinyML. We firstly, present background of TinyML. Secondly, we list the tool sets for supporting TinyML. Thirdly, we present key enablers for improvement of TinyML systems. Fourthly, we present state-of-the-art about frameworks for TinyML. Finally, we identify key challenges and prescribe a future roadmap for mitigating several research issues of TinyML. |
| format | Article |
| id | doaj-e97d7122c56d418eb6fff6461a7061df |
| institution | Directory of Open Access Journals |
| issn | 1319-1578 |
| language | English |
| publishDate | 2022-04-01 |
| publisher | Springer |
| record_format | Article |
| spelling | doaj-e97d7122c56d418eb6fff6461a7061df2025-11-03T01:06:13ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782022-04-013441595162310.1016/j.jksuci.2021.11.019A review on TinyML: State-of-the-art and prospectsPartha Pratim Ray0Department of Computer Applications, Sikkim University, IndiaMachine learning has become an indispensable part of the existing technological domain. Edge computing and Internet of Things (IoT) together presents a new opportunity to imply machine learning techniques at the resource constrained embedded devices at the edge of the network. Conventional machine learning requires enormous amount of power to predict a scenario. Embedded machine learning – TinyML paradigm aims to shift such plethora from traditional high-end systems to low-end clients. Several challenges are paved while doing such transition such as, maintaining the accuracy of learning models, provide train-to-deploy facility in resource frugal tiny edge devices, optimizing processing capacity, and improving reliability. In this paper, we present an intuitive review about such possibilities for TinyML. We firstly, present background of TinyML. Secondly, we list the tool sets for supporting TinyML. Thirdly, we present key enablers for improvement of TinyML systems. Fourthly, we present state-of-the-art about frameworks for TinyML. Finally, we identify key challenges and prescribe a future roadmap for mitigating several research issues of TinyML.http://www.sciencedirect.com/science/article/pii/S1319157821003335TinyMLIoTEdge intelligenceEnergy efficient AIResource constrained intelligenceEmbedded AI |
| spellingShingle | Partha Pratim Ray A review on TinyML: State-of-the-art and prospects TinyML IoT Edge intelligence Energy efficient AI Resource constrained intelligence Embedded AI |
| title | A review on TinyML: State-of-the-art and prospects |
| title_full | A review on TinyML: State-of-the-art and prospects |
| title_fullStr | A review on TinyML: State-of-the-art and prospects |
| title_full_unstemmed | A review on TinyML: State-of-the-art and prospects |
| title_short | A review on TinyML: State-of-the-art and prospects |
| title_sort | review on tinyml state of the art and prospects |
| topic | TinyML IoT Edge intelligence Energy efficient AI Resource constrained intelligence Embedded AI |
| url | http://www.sciencedirect.com/science/article/pii/S1319157821003335 |
| work_keys_str_mv | AT parthapratimray areviewontinymlstateoftheartandprospects AT parthapratimray reviewontinymlstateoftheartandprospects |