Computational Complexity Evaluation of Neural Network Applications in Signal Processing

arXiv:2206.12191v2 Announce Type: replace-cross
Abstract: In this paper, we provide a systematic approach for assessing and comparing the computational complexity of neural network layers in digital signal processing. We provide and link four software-to-hardware complexity measures, defining how the different complexity metrics relate to the layers' hyper-parameters. This paper explains how to compute these four metrics for feed-forward and recurrent layers, and defines in which case we ought to use a particular metric depending on whether we characterize a more …

abstract applications arxiv complexity computational cs.cc cs.lg digital eess.sp evaluation hardware metrics network neural network paper parameters processing signal software type