A new survey paper published on arXiv examines the challenges of on-device learning (ODL) for TinyML applications. It highlights how changes in data distribution after deployment can degrade the performance of static models. The paper surveys approximately 70 ODL works, categorizing them by the type of distribution change they address and analyzing their impact on applications, hardware, and solution structures. A significant gap is noted between current ODL benchmarks and real-world deployment scenarios. AI
IMPACT Identifies a gap between ODL benchmarks and real-world deployment, potentially guiding future research and development in TinyML.
RANK_REASON The cluster contains a survey paper on a specific area of machine learning research.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →