Unsupervised Learning of Variational Autoencoders on Cortex-M Microcontrollers

Deutel M, Plinge A, Seuss D, Mutschler C, Hannig F, Teich J (2025)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Publisher: IEEE

Pages Range: 469-476

Conference Proceedings Title: Proceedings of the IEEE 18th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC)

Event location: Singapore SG

ISBN: 979-8-3315-6571-8

DOI: 10.1109/MCSoC67473.2025.00079

Abstract

Training and fine-tuning deep neural networks (DNNs) to adapt to new and unseen data at the edge has recently attracted considerable research interest. However, most work to date has focused on supervised learning of pre-trained, quantized DNNs. Although these proposed techniques are advantageous in enabling DNN training even on resource-constrained devices such as microcontroller units (MCUs), they do not address the issue that large amounts of labeled data are required to perform supervised training. Moreover, while data are readily available at the edge, ground-truth labels are typically not. In this work, we explore variational autoencoders as a way to train unsupervised, i.e., without labels, feature extractors for image classification on a Cortex-M MCU. Using these feature extractors, we then train classification heads using small labeled representative sets of data to solve classification tasks. Our approach significantly reduces the amount of labeled data required, while enabling full DNN training from scratch on resource-constrained devices.

Authors with CRIS profile

Mark Deutel Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design) Christopher Mutschler
Frank Hannig Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design) Jürgen Teich Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Deutel, M., Plinge, A., Seuss, D., Mutschler, C., Hannig, F., & Teich, J. (2025). Unsupervised Learning of Variational Autoencoders on Cortex-M Microcontrollers. In Proceedings of the IEEE 18th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) (pp. 469-476). Singapore, SG: IEEE.

MLA:

Deutel, Mark, et al. "Unsupervised Learning of Variational Autoencoders on Cortex-M Microcontrollers." Proceedings of the IEEE 18th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC), Singapore IEEE, 2025. 469-476.

BibTeX: Download