Quaternion Neural Network and Its Application

Teijiro Isokawa, Tomoaki Kusakabe, Noriyuki Matsui, and Ferdinand Peper


Abstract
Quaternion neural networks are models of which computations in the neurons is based on quaternions, the four-dimensional equivalents of imaginary numbers. This paper shows by experiments that the quaternion-version of the Back Propagation (BP) Algorithm achieves correct geometrical transformations in color apace for an image compression problem, whereas real-valued BP Algorithms fail.