SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
Abstract
Consumer electronics used to follow the miniaturization trend described by Moore’s Law. Despite increased processing power in Microcontroller Units (MCUs), MCUs used in the smallest appliances are still not capable of running even moderately big, state-of-the-art artificial neural networks (ANNs) especially in time-sensitive scenarios. In this work, we present a novel method called Scattered Online Inference (SOI) that aims to reduce the computational complexity of ANNs. SOI leverages the continuity and seasonality of time-series data and model predictions, enabling extrapolation for processing speed improvements, particularly in deeper layers. By applying compression, SOI generates more general inner partial states of ANN, allowing skipping full model recalculation at each inference.
Cite
Text
Stefański et al. "SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model." Neural Information Processing Systems, 2024. doi:10.52202/079017-0611Markdown
[Stefański et al. "SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/stefanski2024neurips-soi/) doi:10.52202/079017-0611BibTeX
@inproceedings{stefanski2024neurips-soi,
title = {{SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model}},
author = {Stefański, Grzegorz and Daniluk, Paweł and Szumaczuk, Artur and Tkaczuk, Jakub},
booktitle = {Neural Information Processing Systems},
year = {2024},
doi = {10.52202/079017-0611},
url = {https://mlanthology.org/neurips/2024/stefanski2024neurips-soi/}
}