3 citations · 4 across the 4 of their papers we have counts for
3 papers · 1 filter
DRIP: DRop unImportant data Points -- Enhancing Machine Learning Efficiency with Grad-CAM-Based Real-Time Data Prioritization for On-Device Training
Marcus Rüb, Daniel Konegen, Patrick Selle +2
Selecting data points for model training is critical in machine learning. Effective selection methods can reduce the labeling effort, optimize on-device training for embedded syste…
Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation
Marcus Rüb, Axel Sikora, Daniel Mueller-Gritschneder
This study introduces TinyPropv2, an innovative algorithm optimized for on-device learning in deep neural networks, specifically designed for low-power microcontroller units. TinyP…
TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning
Marcus Rüb, Daniel Maier, Daniel Mueller-Gritschneder +1
Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on…