Identifier

etd-07142006-093118

Degree

Master of Science (MS)

Department

Electrical and Computer Engineering

Document Type

Thesis

Abstract

Neural network architectures such as backpropagation networks, perceptrons or generalized Hopfield networks can handle complex inputs but they require a large amount of time and resources for the training process. This thesis investigates instantaneously trained feedforward neural networks that can handle 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.

Date

2006

Document Availability at the Time of Submission

Release the entire work immediately for access worldwide.

Committee Chair

Subhash Kak

Share

COinS