Computational Complexity Evaluation of Neural Network Applications in Signal Processing

TL;DR

This paper introduces a systematic approach and four metrics, including a new one called NABS, for evaluating the computational complexity of neural network layers in digital signal processing, linking software and hardware considerations.

Contribution

It provides a unified framework for complexity assessment, including a novel metric NABS for heterogeneous quantization, applicable to both feed-forward and recurrent layers.

Findings

Four complexity metrics linked to hyper-parameters

Introduction of NABS for heterogeneous quantization

Guidelines for choosing metrics based on application type

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 soft- or hardware-oriented application. One of the four metrics, called `the number of additions and bit shifts (NABS)', is newly introduced for heterogeneous quantization. NABS characterizes the impact of not only the bitwidth used in the operation but also the type of quantization used in the arithmetical operations. We intend this work to serve as a baseline for the different levels (purposes) of complexity estimation related to the neural networks' application in real-time digital signal processing, aiming at unifying the computational complexity estimation.