Neural Networks with Complex and Quaternion Inputs

Preprint English OPEN
Rishiyur, Adityan (2006)
  • Subject: Computer Science - Neural and Evolutionary Computing
    acm: ComputingMethodologies_COMPUTERGRAPHICS | ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION

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.
  • Metrics
    views in OpenAIRE
    views in local repository
    downloads in local repository
Share - Bookmark