id:"swepub:oai:research.chalmers.se:2b70b040-779f-4018-b404-608c9777d675"
Sökning: id:"swepub:oai:research.chalmers.se:2b70b040-779f-4018-b404-608c9777d675" > MicroTL: Transfer L...
- 1 av 1
- Föregående post
- Nästa post
- Till träfflistan
| Fältnamn | Indikatorer | Metadata |
|---|---|---|
| 000 | 03511naa a2200373 4500 | |
| 001 | oai:research.chalmers.se:2b70b040-779f-4018-b404-608c9777d675 | |
| 003 | SwePub | |
| 008 | 220903s2022 | |||||||||||000 ||eng| | |
| 020 | a 9781665480017 | |
| 024 | 7 | a https://research.chalmers.se/publication/5318782 URI |
| 024 | 7 | a https://doi.org/10.1109/LCN53696.2022.98437352 DOI |
| 040 | a (SwePub)cth | |
| 041 | a engb eng | |
| 042 | 9 SwePub | |
| 072 | 7 | a kon2 swepub-publicationtype |
| 072 | 7 | a ref2 swepub-contenttype |
| 100 | 1 | a Profentzas, Christos,d 1989u Chalmers tekniska högskola,Chalmers University of Technology4 aut0 (Swepub:cth)chrpro |
| 245 | 1 0 | a MicroTL: Transfer Learning on Low-Power IoT Devices |
| 264 | 1 | c 2022 |
| 338 | a electronic2 rdacarrier | |
| 520 | a Deep Neural Networks (DNNs) on IoT devices are becoming readily available for classification tasks using sensor data like images and audio. However, DNNs are trained using extensive computational resources such as GPUs on cloud services, and once being quantized and deployed on the IoT device remain unchanged. We argue in this paper, that this approach leads to three disadvantages. First, IoT devices are deployed in real-world scenarios where the initial problem may shift over time (e.g., to new or similar classes), but without re-training, DNNs cannot adapt to such changes. Second, IoT devices need to use energy-preserving communication with limited reliability and network bandwidth, which can delay or restrict the transmission of essential training sensor data to the cloud. Third, collecting and storing training sensor data in the cloud poses privacy concerns. A promising technique to mitigate these concerns is to utilize on-device Transfer Learning (TL). However, bringing TL to resource-constrained devices faces challenges and tradeoffs in computational, energy, and memory constraints, which this paper addresses. This paper introduces MicroTL, Transfer Learning (TL) on low-power IoT devices. MicroTL tailors TL to IoT devices without the communication requirement with the cloud. Notably, we found that the MicroTL takes 3x less energy and 2.8x less time than transmitting all data to train an entirely new model in the cloud, showing that it is more efficient to retrain parts of an existing neural network on the IoT device. | |
| 650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Datavetenskap0 (SwePub)102012 hsv//swe |
| 650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Computer Sciences0 (SwePub)102012 hsv//eng |
| 650 | 7 | a TEKNIK OCH TEKNOLOGIERx Elektroteknik och elektronikx Datorsystem0 (SwePub)202062 hsv//swe |
| 650 | 7 | a ENGINEERING AND TECHNOLOGYx Electrical Engineering, Electronic Engineering, Information Engineeringx Computer Systems0 (SwePub)202062 hsv//eng |
| 653 | a IoT | |
| 653 | a Transfer learning | |
| 700 | 1 | a Almgren, Magnus,d 1972u Chalmers tekniska högskola,Chalmers University of Technology4 aut0 (Swepub:cth)almgren |
| 700 | 1 | a Landsiedel, Olaf,d 1979u Chalmers tekniska högskola,Chalmers University of Technology4 aut0 (Swepub:cth)olafl |
| 710 | 2 | a Chalmers tekniska högskola4 org |
| 773 | 0 | t Proceedings - Conference on Local Computer Networks, LCNg , s. 34-41q <34-41z 9781665480017 |
| 856 | 4 | u https://research.chalmers.se/publication/533597/file/533597_Fulltext.pdfx primaryx freey FULLTEXT |
| 856 | 4 8 | u https://research.chalmers.se/publication/531878 |
| 856 | 4 8 | u https://doi.org/10.1109/LCN53696.2022.9843735 |
Hitta via bibliotek
- Proceedings - Conference on Local Computer Networks, LCN (Sök värdpublikationen i LIBRIS)
Till lärosätets databas
- 1 av 1
- Föregående post
- Nästa post
- Till träfflistan
Hitta mer i SwePub
- Av författaren/redakt...
- Profentzas, Chri ...
- Almgren, Magnus, ...
- Landsiedel, Olaf ...
- Om ämnet
-
- NATURVETENSKAP
- NATURVETENSKAP
- och Data och informa ...
- och Datavetenskap
-
- TEKNIK OCH TEKNOLOGIER
- TEKNIK OCH TEKNO ...
- och Elektroteknik oc ...
- och Datorsystem
- Artiklar i publikationen
- Proceedings - Co ...
- Av lärosätet
- Chalmers tekniska högskola
Sök utanför SwePub
- Sök vidare i:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - Nationella bibliotekssystem
- LIBRIS.kb.se
