4 papers
Design-Time Optimization of Deep Neural Networks for Intermittent Learning on Microcontrollers
Jakob Schubert, Maximilian Kasper, Maximilian Linke +5
We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs). In mobile applications where…
Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
Lucas Heublein, Mark Deutel, Axel Plinge +1
Embedded global navigation satellite system (GNSS) interference monitoring requires fast and memory-efficient inference to process large volumes of raw in-phase and quadrature (IQ)…
microYOLO: Towards Single-Shot Object Detection on Microcontrollers
Mark Deutel, Christopher Mutschler, Jürgen Teich
This work-in-progress paper presents results on the feasibility of single-shot object detection on microcontrollers using YOLO. Single-shot object detectors like YOLO are widely us…
On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers
Mark Deutel, Frank Hannig, Christopher Mutschler +1
On-device training of DNNs allows models to adapt and fine-tune to newly collected data or changing domains while deployed on microcontroller units (MCUs). However, DNN training is…