Root-Power Mean Aggregation-Based Neuron in Quaternionic Domain. Issue 4 (4th July 2019)

• Record Type: Journal Article
• Authors: Kumar, Sushil; Tripathi, Bipin Kumar
• Is Part Of: IETE journal of research. Volume 65:Issue 4(2019)
• Page Start: 557
• Page End: 575
• Publication Date: 2019-07-04
• Subjects: Approximation -- Quasi-arithmetic means -- Quaternionic resilient propagation -- Quaternionic-valued back-propagation -- Quaternionic-valued function -- Quaternionic-valued multilayer perceptron -- Root-power means in quaternionic domain (ℍ) -- Three-dimensional face recognition; Electronics -- Periodicals; Telecommunication -- Periodicals; Electronics; Telecommunication; Periodicals; 621.38
• DOI: 10.1080/03772063.2018.1436473
• Languages: English
• ISSNs: 0377-2063

Abstract

ABSTRACT: This paper illustrates the new structure of artificial neuron based on root-power mean (RPM) aggregation for quaternionic-valued signals and also presented an efficient learning process of neural networks with quaternionic-valued RPM neurons. The main aim of this neuron is to present the potential capability of a nonlinear aggregation operation on the quaternionic-valued signals in neuron cell. A wide spectrum of aggregation ability of RPM in between minima and maxima has a beautiful property of changing its degree of compensation in the natural way which emulates the various existing neuron models as its special cases. Further, the quaternionic resilient propagation algorithm (ℍ-RPROP) with error-dependent weight backtracking step significantly accelerates the training speed and exhibits better approximation accuracy. The wide spectra of benchmark problem are considered to evaluate the performance of proposed quaternionic RPM neuron with ℍ-RPROP learning algorithm.