On the learning machine with compensatory aggregation based neurons in quaternionic domain

Author:

Kumar Sushil1,Tripathi Bipin Kumar1

Affiliation:

1. Department of Computer Science & Engineering, Harcourt Butler Technical University, Kanpur 208002, Uttar Pradesh, India

Abstract

Abstract The nonlinear spatial grouping process of synapses is one of the fascinating methodologies for neuro-computing researchers to achieve the computational power of a neuron. Generally, researchers use neuron models that are based on summation (linear), product (linear) or radial basis (nonlinear) aggregation for the processing of synapses, to construct multi-layered feed-forward neural networks, but all these neuron models and their corresponding neural networks have their advantages or disadvantages. The multi-layered network generally uses for accomplishing the global approximation of input–output mapping but sometimes getting stuck into local minima, while the nonlinear radial basis function (RBF) network is based on exponentially decaying that uses for local approximation to input–output mapping. Their advantages and disadvantages motivated to design two new artificial neuron models based on compensatory aggregation functions in the quaternionic domain. The net internal potentials of these neuron models are developed with the compositions of basic summation (linear) and radial basis (nonlinear) operations on quaternionic-valued input signals. The neuron models based on these aggregation functions ensure faster convergence, better training, and prediction accuracy. The learning and generalization capabilities of these neurons are verified through various three-dimensional transformations and time series predictions as benchmark problems. Highlights Two new CSU and CPU neuron models for quaternionic signals are proposed. Net potentials based on the compositions of summation and radial basis functions. The nonlinear grouping of synapses achieve the computational power of proposed neurons. The neuron models ensure faster convergence, better training and prediction accuracy. The learning and generalization capabilities of CSU/CPU are verified by various benchmark problems.

Publisher

Oxford University Press (OUP)

Subject

Computational Mathematics,Computer Graphics and Computer-Aided Design,Human-Computer Interaction,Engineering (miscellaneous),Modelling and Simulation,Computational Mechanics

Reference34 articles.

1. Quaternionic multilayer perceptrons for chaotic time series prediction;Arena;IEICE Transactions on Fundamentals,1996

2. Multilayer perceptrons to approximate quaternion valued functions;Arena;Neural Networks,1997

3. On the complex back-propagation algorithm;Benvenuto;I EEE Transactions on Signal Processing,1992

4. New neuron models for simulating rotating electrical machines and load forecasting problems;Chaturvedi;Electric Power Systems Research,1999

5. An modified error function for the complex-value backpropagation neural networks;Chen;Neural Information Processing,2005

Cited by 8 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3