On-device Personalization on tiny MCUs
Project Description
With the proliferation of tiny devices such as Microcontrollers (MCUs) with a few Megabytes of memory and storage, many researchers and machine learning (ML) practitioners have paid attention to the possibility of the model adaptation on-device. The ability of the deployed models to continually learn to dynamically incorporate new tasks and changing input distribution from users becomes essential for both efficiency and user privacy. However, there is no existing framework that enables on-device training/adaptation/personalization on tiny MCUs.
In this work, we want to develop the on-device personalization on severely resource-constrained devices having less than 1 MB RAM and 2 MB flash memory (e.g., STM32 Microcontroller).
Contact: Interested students can actively discuss and suggest their ideas and also contact Young D. Kwon (ydk21@cam.ac.uk), Jagmohan Chauhan (jc2161@cam.ac.uk/J.Chauhan@soton.ac.uk, and Pan Hui (panhui@ust.hk) for more details.
Reference papers (can be a good starting point)
[1] 2021. MLSys. TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems. Robert David et al.
[2] 2019. ArXiv. On-Device Neural Net Inference with Mobile GPUs. Juhyun Lee et al.
In this work, we want to develop the on-device personalization on severely resource-constrained devices having less than 1 MB RAM and 2 MB flash memory (e.g., STM32 Microcontroller).
Contact: Interested students can actively discuss and suggest their ideas and also contact Young D. Kwon (ydk21@cam.ac.uk), Jagmohan Chauhan (jc2161@cam.ac.uk/J.Chauhan@soton.ac.uk, and Pan Hui (panhui@ust.hk) for more details.
Reference papers (can be a good starting point)
[1] 2021. MLSys. TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems. Robert David et al.
[2] 2019. ArXiv. On-Device Neural Net Inference with Mobile GPUs. Juhyun Lee et al.
Supervisor
HUI Pan
Quota
3
Course type
UROP1000
UROP1100
UROP2100
UROP3100
UROP4100
Applicant's Roles
Required skills/aptitudes to successfully complete the project are:
1. Self-motivated and proactive, which means you should be able to set your own milestones and finish them on time.
2. Embedded software/hardware knowledge, basic knowledge of how neural networks work.
3.Understanding of frameworks for the development (e.g., TensorFlow Lite, TensorFlow Lite Micro) is a plus.
1. Self-motivated and proactive, which means you should be able to set your own milestones and finish them on time.
2. Embedded software/hardware knowledge, basic knowledge of how neural networks work.
3.Understanding of frameworks for the development (e.g., TensorFlow Lite, TensorFlow Lite Micro) is a plus.
Applicant's Learning Objectives
Benefits of participating in this project are:
1. Opportunity to gain hands-on experience in on-device ML/DL research.
2. Opportunity to tackle a challenging and novel problem that no one has solved before.
3. Opportunity for having a top-tier academic publication, depending on the quality and the amount of novel contribution of the project.
1. Opportunity to gain hands-on experience in on-device ML/DL research.
2. Opportunity to tackle a challenging and novel problem that no one has solved before.
3. Opportunity for having a top-tier academic publication, depending on the quality and the amount of novel contribution of the project.
Complexity of the project
Challenging