DRIP: DRop unImportant data Points - Enhancing Machine Learning Efficiency with Grad-CAM-Based Real-Time Data Prioritization for On-Device Training.
CoRR, April, 2025
Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation.
Proceedings of the International Joint Conference on Neural Networks, 2024
A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption.
Proceedings of the 7th IEEE International Conference on Industrial Cyber-Physical Systems, 2024
TinyProp - Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning.
CoRR, 2023