On the Computational Complexities of Complex-valued Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mayer, Kayol Soares, Soares, Jonathan Aguiar, Cruz, Ariadne Arrais, Arantes, Dalton Soares
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929463614242816
author Mayer, Kayol Soares
Soares, Jonathan Aguiar
Cruz, Ariadne Arrais
Arantes, Dalton Soares
author_facet Mayer, Kayol Soares
Soares, Jonathan Aguiar
Cruz, Ariadne Arrais
Arantes, Dalton Soares
contents Complex-valued neural networks (CVNNs) are nonlinear filters used in the digital signal processing of complex-domain data. Compared with real-valued neural networks~(RVNNs), CVNNs can directly handle complex-valued input and output signals due to their complex domain parameters and activation functions. With the trend toward low-power systems, computational complexity analysis has become essential for measuring an algorithm's power consumption. Therefore, this paper presents both the quantitative and asymptotic computational complexities of CVNNs. This is a crucial tool in deciding which algorithm to implement. The mathematical operations are described in terms of the number of real-valued multiplications, as these are the most demanding operations. To determine which CVNN can be implemented in a low-power system, quantitative computational complexities can be used to accurately estimate the number of floating-point operations. We have also investigated the computational complexities of CVNNs discussed in some studies presented in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13075
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Computational Complexities of Complex-valued Neural Networks
Mayer, Kayol Soares
Soares, Jonathan Aguiar
Cruz, Ariadne Arrais
Arantes, Dalton Soares
Neural and Evolutionary Computing
Machine Learning
Signal Processing
Complex-valued neural networks (CVNNs) are nonlinear filters used in the digital signal processing of complex-domain data. Compared with real-valued neural networks~(RVNNs), CVNNs can directly handle complex-valued input and output signals due to their complex domain parameters and activation functions. With the trend toward low-power systems, computational complexity analysis has become essential for measuring an algorithm's power consumption. Therefore, this paper presents both the quantitative and asymptotic computational complexities of CVNNs. This is a crucial tool in deciding which algorithm to implement. The mathematical operations are described in terms of the number of real-valued multiplications, as these are the most demanding operations. To determine which CVNN can be implemented in a low-power system, quantitative computational complexities can be used to accurately estimate the number of floating-point operations. We have also investigated the computational complexities of CVNNs discussed in some studies presented in the literature.
title On the Computational Complexities of Complex-valued Neural Networks
topic Neural and Evolutionary Computing
Machine Learning
Signal Processing
url https://arxiv.org/abs/2310.13075