SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Stefański, Grzegorz, Daniluk, Paweł, Szumaczuk, Artur, Tkaczuk, Jakub
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914966406168576
author Stefański, Grzegorz
Daniluk, Paweł
Szumaczuk, Artur
Tkaczuk, Jakub
author_facet Stefański, Grzegorz
Daniluk, Paweł
Szumaczuk, Artur
Tkaczuk, Jakub
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03813
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
Stefański, Grzegorz
Daniluk, Paweł
Szumaczuk, Artur
Tkaczuk, Jakub
Machine Learning
Sound
Audio and Speech Processing
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.
title SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
topic Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2410.03813