English

Rapid Exact Signal Scanning with Deep Convolutional Neural Networks

Machine Learning 2017-08-03 v5 Computer Vision and Pattern Recognition Neural and Evolutionary Computing

Abstract

A rigorous formulation of the dynamics of a signal processing scheme aimed at dense signal scanning without any loss in accuracy is introduced and analyzed. Related methods proposed in the recent past lack a satisfactory analysis of whether they actually fulfill any exactness constraints. This is improved through an exact characterization of the requirements for a sound sliding window approach. The tools developed in this paper are especially beneficial if Convolutional Neural Networks are employed, but can also be used as a more general framework to validate related approaches to signal scanning. The proposed theory helps to eliminate redundant computations and renders special case treatment unnecessary, resulting in a dramatic boost in efficiency particularly on massively parallel processors. This is demonstrated both theoretically in a computational complexity analysis and empirically on modern parallel processors.

Keywords

Cite

@article{arxiv.1508.06904,
  title  = {Rapid Exact Signal Scanning with Deep Convolutional Neural Networks},
  author = {Markus Thom and Franz Gritschneder},
  journal= {arXiv preprint arXiv:1508.06904},
  year   = {2017}
}

Comments

Pages 1-16 only: Copyright (c) 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission

R2 v1 2026-06-22T10:42:59.967Z