IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Quaternionic Neural Networks: Fundamental Properties and Applications

Quaternionic Neural Networks: Fundamental Properties and Applications
View Sample PDF
Author(s): Teijiro Isokawa (University of Hyogo, Japan), Nobuyuki Matsui (University of Hyogo, Japan) and Haruhiko Nishimura (University of Hyogo, Japan)
Copyright: 2009
Pages: 29
Source title: Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters
Source Author(s)/Editor(s): Tohru Nitta (National Institute of Advanced Industrial Science and Technology, Japan)
DOI: 10.4018/978-1-60566-214-5.ch016

Purchase

View Quaternionic Neural Networks: Fundamental Properties and Applications on the publisher's website for pricing and purchasing information.

Abstract

Quaternions are a class of hypercomplex number systems, a four-dimensional extension of imaginary numbers, which are extensively used in various fields such as modern physics and computer graphics. Although the number of applications of neural networks employing quaternions is comparatively less than that of complex-valued neural networks, it has been increasing recently. In this chapter, the authors describe two types of quaternionic neural network models. One type is a multilayer perceptron based on 3D geometrical affine transformations by quaternions. The operations that can be performed in this network are translation, dilatation, and spatial rotation in three-dimensional space. Several examples are provided in order to demonstrate the utility of this network. The other type is a Hopfield-type recurrent network whose parameters are directly encoded into quaternions. The stability of this network is demonstrated by proving that the energy decreases monotonically with respect to the change in neuron states. The fundamental properties of this network are presented through the network with three neurons.

Related Content

Arunaben Prahladbhai Gurjar, Shitalben Bhagubhai Patel. © 2022. 30 pages.
Meghna Babubhai Patel, Jagruti N. Patel, Upasana M. Bhilota. © 2022. 10 pages.
Vo Ngoc Phu, Vo Thi Ngoc Tran. © 2022. 27 pages.
Steven Walczak. © 2022. 17 pages.
Priyanka P. Patel, Amit R. Thakkar. © 2022. 26 pages.
Vo Ngoc Phu, Vo Thi Ngoc Tran. © 2022. 34 pages.
Sarat Chandra Nayak, Subhranginee Das, Bijan Bihari Misra. © 2022. 20 pages.
Body Bottom