Sorry, you need to enable JavaScript to visit this website.

Complex-Valued Vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data

Primary tabs

Citation Author(s):
J. A. Barrachina, C. Ren, C. Morisseau, G. Vieillard, J.-P. Ovarlez
Submitted by:
Agusstin Barrachina
Last updated:
23 June 2021 - 7:54am
Document Type:
Poster
Document Year:
2021
Event:
Presenters Name:
J Agustin BARRACHINA
Paper Code:
MLSP-9.6

Abstract 

Abstract: 

This paper shows the benefits of using Complex-Valued Neural Network (CVNN) on classification tasks for non-circular complex-valued datasets. Motivated by radar and especially Synthetic Aperture Radar (SAR) applications, we propose a statistical analysis of fully connected feed-forward neural networks performance in the cases where real and imaginary parts of the data are correlated through the non-circular property. In this context, comparisons between CVNNs and their real-valued equivalent models are conducted, showing that CVNNs provide better performance for multiple types of non-circularity. Notably, CVNNs statistically perform less overfitting, higher accuracy and provide shorter confidence intervals than its equivalent Real-Valued Neural Network (RVNN).

up
0 users have voted:

Dataset Files

Poster presentation ICASSP 2021 MLSP-9.6

(38)