Neural Networks with Complex and Quaternion Inputs

2006/07/18 by Adityan Rishiyur, Rishiyur, Adityan
Computer Science · #FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE) #cs.NE

paper · pdf · doi:10.48550/arxiv.cs/0607090

14 pages, 2 figures

arxiv created 2006/07/18 · arxiv updated 2009/12/01

Abstract

This article investigates Kak neural networks, which can be instantaneously trained, for complex and quaternion inputs. The performance of the basic algorithm has been analyzed and shown how it provides a plausible model of human perception and understanding of images. The motivation for studying quaternion inputs is their use in representing spatial rotations that find applications in computer graphics, robotics, global navigation, computer vision and the spatial orientation of instruments. The problem of efficient mapping of data in quaternion neural networks is examined. Some problems that need to be addressed before quaternion neural networks find applications are identified.

Related

• Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
• 3D-Rotation-Equivariant Quaternion Neural Networks
• Learning Characteristics of Reverse Quaternion Neural Network
• Quaternion Convolutional Neural Networks
• Improving Quaternion Neural Networks with Quaternionic Activation Functions