Search
 
loader loading subjects...
cover
Quaternion Phase CNN
E. Ulises Moya-Sánchez, Sebastian Colores, Abraham Sánchez, Ulises Cortés
89 - 95
10.3233/978-1-61499-918-8-89
Frontiers in Artificial Intelligence and Applications
Volume 308: Artificial Intelligence Research and Development
Abstract

The main aim of this work is to present a Quaternion Phase Convolutional Neural Network. We encode 3 quaternion phases and its magnitude as an input. Our approach is bio-inspired and is expressed in one mathematical framework. The main result is to obtain a new space feature representation for deep learning which can capture non-trivial equivariant features, related to illumination, and rotation.

$35.00 / €27.50 / £22.00
Add PDF to cart