Next Article in Journal
A General Overview of Scientific Production in China, Japan and Korea of the Water-Gas Shift (WGS) Process
Previous Article in Journal
Information and Energy/Matter
Previous Article in Special Issue
Fröhlich Condensate: Emergence of Synergetic Dissipative Structures in Information Processing Biological and Condensed Matter Systems
Information 2012, 3(4), 756-770; doi:10.3390/info3040756
Article

Quaternionic Multilayer Perceptron with Local Analyticity

1,* , 2
 and
1
Received: 11 September 2012 / Revised: 13 November 2012 / Accepted: 20 November 2012 / Published: 28 November 2012
(This article belongs to the Special Issue Brain like Computing, Communication and Machines)
View Full-Text   |   Download PDF [155 KB, uploaded 28 November 2012]   |   Browse Figures

Abstract

A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this network. An error back-propagation algorithm is introduced for modifying the connection weights of the network.
Keywords: quaternion; local analyticity; Wirtinger calculus; multilayer perceptron; error back-propagation quaternion; local analyticity; Wirtinger calculus; multilayer perceptron; error back-propagation
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Share & Cite This Article

Further Mendeley | CiteULike
Export to BibTeX |
EndNote
MDPI and ACS Style

Isokawa, T.; Nishimura, H.; Matsui, N. Quaternionic Multilayer Perceptron with Local Analyticity. Information 2012, 3, 756-770.

View more citation formats

Article Metrics

Comments

Citing Articles

[Return to top]
Information EISSN 2078-2489 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert