Next Article in Journal
Open Innovation Engineering—Preliminary Study on New Entrance of Technology to Market
Next Article in Special Issue
Detecting Predictable Segments of Chaotic Financial Time Series via Neural Network
Previous Article in Journal
Facilitating Autonomous Systems with AI-Based Fault Tolerance and Computational Resource Economy
Previous Article in Special Issue
Automatic Sleep Disorders Classification Using Ensemble of Bagged Tree Based on Sleep Quality Features
Open AccessArticle

Validation of Large-Scale Classification Problem in Dendritic Neuron Model Using Particle Antagonism Mechanism

1
School of Computer Engineering, Jiangsu Ocean University, Lianyungang 222005, China
2
Department of Management, eSOL Co., Ltd., Tokyo 164-8721, Japan
3
Faculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa-shi 920-1192, Japan
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(5), 792; https://doi.org/10.3390/electronics9050792
Received: 15 April 2020 / Revised: 27 April 2020 / Accepted: 1 May 2020 / Published: 11 May 2020
(This article belongs to the Special Issue Applications of Bioinspired Neural Network)
With the characteristics of simple structure and low cost, the dendritic neuron model (DNM) is used as a neuron model to solve complex problems such as nonlinear problems for achieving high-precision models. Although the DNM obtains higher accuracy and effectiveness than the middle layer of the multilayer perceptron in small-scale classification problems, there are no examples that apply it to large-scale classification problems. To achieve better performance for solving practical problems, an approximate Newton-type method-neural network with random weights for the comparison; and three learning algorithms including back-propagation (BP), biogeography-based optimization (BBO), and a competitive swarm optimizer (CSO) are used in the DNM in this experiment. Moreover, three classification problems are solved by using the above learning algorithms to verify their precision and effectiveness in large-scale classification problems. As a consequence, in the case of execution time, DNM + BP is the optimum; DNM + CSO is the best in terms of both accuracy stability and execution time; and considering the stability of comprehensive performance and the convergence rate, DNM + BBO is a wise choice. View Full-Text
Keywords: neuron model; large-scale classification problem; dendritic neuron model (DNM); learning algorithm; neural network neuron model; large-scale classification problem; dendritic neuron model (DNM); learning algorithm; neural network
Show Figures

Graphical abstract

MDPI and ACS Style

Jia, D.; Fujishita, Y.; Li, C.; Todo, Y.; Dai, H. Validation of Large-Scale Classification Problem in Dendritic Neuron Model Using Particle Antagonism Mechanism. Electronics 2020, 9, 792. https://doi.org/10.3390/electronics9050792

AMA Style

Jia D, Fujishita Y, Li C, Todo Y, Dai H. Validation of Large-Scale Classification Problem in Dendritic Neuron Model Using Particle Antagonism Mechanism. Electronics. 2020; 9(5):792. https://doi.org/10.3390/electronics9050792

Chicago/Turabian Style

Jia, Dongbao; Fujishita, Yuka; Li, Cunhua; Todo, Yuki; Dai, Hongwei. 2020. "Validation of Large-Scale Classification Problem in Dendritic Neuron Model Using Particle Antagonism Mechanism" Electronics 9, no. 5: 792. https://doi.org/10.3390/electronics9050792

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop