Rapid Exact Signal Scanning with Deep Convolutional Neural Networks

TL;DR

This paper introduces a rigorous theoretical framework for dense signal scanning using deep convolutional neural networks, ensuring exactness and significantly improving computational efficiency on parallel processors.

Contribution

It provides the first formal analysis of exact signal scanning with CNNs, enabling validation and optimization of such methods for high efficiency.

Findings

Theoretical complexity analysis shows significant efficiency gains.

Empirical results confirm improved speed on parallel hardware.

Framework ensures exactness in dense signal scanning with CNNs.

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.