TinyDéjàVu turns time-series neural-network layers into streaming buffers (SSMs), cutting peak RAM by up to 99% and redundant compute on overlapping windows for microcontroller inference.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TinyD\'ej\`aVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams
TinyDéjàVu turns time-series neural-network layers into streaming buffers (SSMs), cutting peak RAM by up to 99% and redundant compute on overlapping windows for microcontroller inference.