paper-with-me

Papers

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

2024-10-04 · Grzegorz Stefański, Paweł Daniluk, Artur Szumaczuk, Jakub Tkaczuk

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.

📄 PDF Abstract BibTeX arXiv:2410.03813

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Provable Target Sample Complexity Improvements as Pre-Trained Models Scale

2026-02-04 · Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui arxiv

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, w…

parameter-efficient fine-tuning

Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling

2023-05-23 · Qidong Yang, Alex Hernandez-Garcia, Paula Harder, Venkatesh Ramesh 외

Climate simulations are essential in guiding our understanding of climate change and responding to its effects. However, it is computationally expensive to resolve complex climate processes at high spatial resolution. As…

Zero-shot Generalization

Capturing Climatic Variability: Using Deep Learning for Stochastic Downscaling

2024-05-31 · Kiri Daust, Adam Monahan

Adapting to the changing climate requires accurate local climate information, a computationally challenging problem. Recent studies have used Generative Adversarial Networks (GANs), a type of deep learning, to learn comp…

Deep Learning

Time-aware UNet and super-resolution deep residual networks for spatial downscaling

2025-12-15 · Mika Sipilä, Sabrina Maggio, Sandra De Iaco, Klaus Nordhausen 외 arxiv

Satellite data of atmospheric pollutants are often available only at coarse spatial resolution, limiting their applicability in local-scale environmental analysis and decision-making. Spatial downscaling methods aim to t…

MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling

2024-08-20 · Zili Liu, Hao Chen, Lei Bai, Wenyuan Li 외

In an era of frequent extreme weather and global warming, obtaining precise, fine-grained near-surface weather forecasts is increasingly essential for human activities. Downscaling (DS), a crucial task in meteorological …

MambaSuper-Resolution