Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors. (arXiv:2209.00591v1 [cs.LG])

Tiny machine learning (TinyML) in IoT systems exploits MCUs as edge devices
for data processing. However, traditional TinyML methods can only perform
inference, limited to static environments or classes. Real case scenarios
usually work in dynamic environments, thus drifting the context where the
original neural model is no more suitable. For this reason, pre-trained models
reduce accuracy and reliability during their lifetime because the data recorded
slowly becomes obsolete or new patterns appear. Continual learning strategies
maintain the model up …

algorithms arxiv comparison incremental learning online learning sensors smart