Rapid Exact Signal Scanning with Deep Convolutional Neural Networks
This provides a general framework to validate signal scanning methods, especially beneficial for Convolutional Neural Networks, though it is incremental in improving analysis and efficiency.
The paper tackles the problem of dense signal scanning without accuracy loss by introducing a rigorous formulation and analysis of exactness constraints, resulting in a dramatic efficiency boost on parallel processors.
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.