SwePub
Sök i LIBRIS databas

  Utökad sökning

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...

  • Profentzas, Christos,1989Chalmers tekniska högskola,Chalmers University of Technology (författare)

MicroTL: Transfer Learning on Low-Power IoT Devices

  • Artikel/kapitelEngelska2022

Förlag, utgivningsår, omfång ...

  • 2022
  • electronicrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:research.chalmers.se:2b70b040-779f-4018-b404-608c9777d675
  • ISBN:9781665480017
  • https://research.chalmers.se/publication/531878URI
  • https://doi.org/10.1109/LCN53696.2022.9843735DOI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:kon swepub-publicationtype
  • Ämneskategori:ref swepub-contenttype

Anmärkningar

  • 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.

Ämnesord och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Almgren, Magnus,1972Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)almgren (författare)
  • Landsiedel, Olaf,1979Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)olafl (författare)
  • Chalmers tekniska högskola (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:Proceedings - Conference on Local Computer Networks, LCN, s. 34-419781665480017

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Sök utanför SwePub

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.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy