mlsanityData to 7 Oct 2026

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

arXiv 2410.03813 ↗First posted 4 Oct 2024cs.LG cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

19 of 35 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  3. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  4. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  5. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  6. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  7. 2019GhostNet: More Features from Cheap Operationscited by 410
  8. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  9. 2017Adaptive Neural Networks for Efficient Inferencecited by 161
  10. 2017Convolutional Networks with Adaptive Inference Graphscited by 147
  11. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 128
  12. 2017Skip RNN: Learning to Skip State Updates in Recurrent Neural Networkscited by 49
7 more
  1. 2020Super-Human Performance in Online Low-latency Recognition of Conversational Speechcited by 20
  2. 2017Learning to Skim Textcited by 18
  3. 2019Neural Speed Reading with Structural-Jump-LSTMcited by 17
  4. 2017Neural Speed Reading via Skim-RNNcited by 14
  5. 2016Variable Computation in Recurrent Neural Networkscited by 10
  6. 2023Short-Term Memory Convolutionscited by 3
  7. 2020Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networkscited by 2

Built on by

Not cited yet.