# TinyD'ej`aVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams

arXiv: https://arxiv.org/abs/2512.09786 · HTML: https://mlsanity.com/paper/2512.09786/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [Time Series Prediction using Deep Learning Methods in Healthcare](https://mlsanity.com/paper/2108.13461/) (2021)
- [Deep Learning for Time-Series Analysis](https://mlsanity.com/paper/1701.01887/) (2017)
- [A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU](https://mlsanity.com/paper/2305.17473/) (2023)
- [Fast Wavenet Generation Algorithm](https://mlsanity.com/paper/1611.09482/) (2016)
- [TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference](https://mlsanity.com/paper/2203.12925/) (2022)
- [TinyChirp: Bird Song Recognition Using TinyML Models on Low-power Wireless Acoustic Sensors](https://mlsanity.com/paper/2407.21453/) (2024)
- [msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML](https://mlsanity.com/paper/2505.11483/) (2025)
- [Don't Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs](https://mlsanity.com/paper/2408.03223/) (2024)
- [A 1-D CNN inference engine for constrained platforms](https://mlsanity.com/paper/2501.17269/) (2025)

## Built on by (most cited first, 1 of 1)

- [PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors](https://mlsanity.com/paper/2608.23101/) (2026)

## 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.