TinyD'ej`aVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams
Not on the map. Why?
Abstract (arXiv)
Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to continuously perform inference on time-series of the data they sense. In order to fit lifetime and energy consumption requirements when operating on battery, such hardware is exclusively based on microcontroller with as little memory as possible, e.g., 128 kB of RAM. In this context, optimizing data flows during inference across neural network layers becomes crucial. In this paper, we introduce a new framework, TinyD'ej`aVu, and novel algorithms we designed to drastically reduce the RAM budget required by inference using various neural network models for sensor data time-series on typical microcontroller hardware. We publish the implementation of TinyD'ej`aVu as open source, and we perform reproducible benchmarks on common microcontroller hardware (Arm Cortex-M). We show that TinyD'ej`aVu can save up to 90% of RAM usage with equal compute latency compared to prior work (StreamiNNC) on overlapping sliding window inputs.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 30 references that are in the map. First posted on arXiv 10 Dec 2025.
Builds on
18 of 30 references.
References · 18
- 2017Attention Is All You Needcited by 59,932
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
- 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
- 2018Deep learning for time series classification: a reviewcited by 575
- 2022Transformers in Time Series: A Surveycited by 489
- 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
- 2019A Study of BFLOAT16 for Deep Learning Trainingcited by 227
- 2021Time Series Prediction using Deep Learning Methods in Healthcarecited by 71
- 2017Deep Learning for Time-Series Analysiscited by 55
- 2023A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRUcited by 25
6 more
- 2016Fast Wavenet Generation Algorithmcited by 14
- 2022TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inferencecited by 4
- 2024TinyChirp: Bird Song Recognition Using TinyML Models on Low-power Wireless Acoustic Sensorscited by 4
- 2025msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyMLcited by 3
- 2024Don't Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNscited by 1
- 2025A 1-D CNN inference engine for constrained platformscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.