Modified artificial neural network model

Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (9): 64-66.

• 理论研究 • Previous Articles Next Articles

Modified artificial neural network model

ZHOU Xiao-zheng¹,LIN Xiao-zhu¹,CHEN Xing²,LI Yu-long³

1.School of Information Engineering，Beijing Institute of Petro-Chemical Technology，Beijing 102617，China
2.School of Electronic and Information Engineering，Beijing University of Aeronautics and Astronautics，Beijing 100083，China
3.Department of Electronic Information，Chonnam National University，Jeollanam-do 550-749，South Korea

Received:2007-07-16 Revised:2007-10-18 Online:2008-03-21 Published:2008-03-21
Contact: ZHOU Xiao-zheng

一种改进的人工神经网络模型

周晓正¹,林小竹¹,陈星²,李玉龙³

1.北京石油化工学院信息工程学院，北京 102617
2.北京航空航天大学电子信息工程学院，北京 100083
3.全南大学电子通信工学科，韩国全罗南道 550-749

通讯作者: 周晓正

Abstract

Abstract: In this paper，a new kind of artificial neural network is proposed，which is called Pattern-Neuron Based Artificial Neural Network（PNBANN）.Different from the current neurocomputing networks，PNBANN is based on neuron connecting completely.Each neuron in PNBANN uniquely represents a pattern.Whenever an unknown pattern is received，a new neuron corresponding to this pattern is produced，and then the information is stored in the PNBANN.If a pattern has existed in the network when it is received，the connections included in the existing pattern neuron structure are enhanced.When the output of a pattern neuron exceeds the given feeling threshold，the pattern is memorized.Therefore，PNBANN can easily receive and store information constantly，and memorizes the information or patterns which can result strong feeling.This process is quite similar to the process of human brain to learn and keep something in mind.Simulations are made in this paper，and the results show that PNBANN can study with very high efficiency，and the existing patterns are not influenced while new pattern are incoming.It is also verified that PNBANN has a very high performance in recognition.

Key words: pattern-neuron, artificial neural network, feeling threshold

摘要： 提出一种新型人工神经网络模型，称为“基于模式神经元的人工神经网络（Pattern Neuron Based Artificial Neural Network，PNBANN）”。与现有的神经计算网络不同，PNBANN是一种完全基于神经元连接的网络模型。网络中的每一个神经元都唯一代表一种模式，每当接收新模式时，自动建立一个新的连接，把信息存储在网络中；而接收已有的模式时，已有的神经元连接得到加强。当模式神经元的输出达到所设定的感觉阈值时，对应模式的信息被记忆。因此，PNBANN就是不断地接收、存储各种信息，并把感觉足够强的模式记忆下来，这一过程更接近于人脑的学习、记忆过程。实验结果证明，PNBANN学习效率高，在学习新知识时不会影响已有的知识，同时具有很强的识别能力。

关键词: 模式神经元, 人工神经网络, 感觉阈值

ZHOU Xiao-zheng¹,LIN Xiao-zhu¹,CHEN Xing²,LI Yu-long³. Modified artificial neural network model[J]. Computer Engineering and Applications, 2008, 44(9): 64-66.

周晓正¹,林小竹¹,陈星²,李玉龙³. 一种改进的人工神经网络模型[J]. 计算机工程与应用, 2008, 44(9): 64-66.

[1]	YAO Yuan, ZHANG Zhaoyang. Stock Index Price Forecasting Method Based on HP Filter [J]. Computer Engineering and Applications, 2021, 57(24): 296-304.
[2]	XUE Wenlong, YU Jiong, GUO Zhiqi, LI Ziyang. End-to-End Encrypted Traffic Classification Based on Feature Fusion Convolutional Neural Network [J]. Computer Engineering and Applications, 2021, 57(18): 114-121.
[3]	ZHANG Chi, GUO Yuan, LI Ming. Review of Development and Application of Artificial Neural Network Models [J]. Computer Engineering and Applications, 2021, 57(11): 57-69.
[4]	LI Jieqi, HU Liangbing. Review of Machine Learning for Predictive Maintenance [J]. Computer Engineering and Applications, 2020, 56(21): 11-19.
[5]	ZHANG Wenjing, CHEN Zhiya, FENG Fenling, LI Wan. Application of Deep Auto-Encoder Based on Sparse Theory in Highway Accident Casualty Forecast [J]. Computer Engineering and Applications, 2019, 55(7): 241-247.
[6]	WANG Haiyan1，2, YUAN Xueqin1, SONG Chao1, ZHANG Zhengyong1，2, LIU Jun1，2, SHA Min1，2. Identification of apple essences based on similarity analysis and artificial neural network [J]. Computer Engineering and Applications, 2018, 54(4): 141-147.
[7]	SONG Qian, GUO Yu, WANG Falin. Comprehensive evaluation method of cable harness wiring quality based on artificial neural network [J]. Computer Engineering and Applications, 2018, 54(14): 256-263.
[8]	YAN Dan, JIANG Jiafu. Marginal Fisher analysis algorithm based on stacked denoising autoencoders [J]. Computer Engineering and Applications, 2017, 53(5): 134-139.
[9]	BAI Cong1，2, PENG Zhongren1，3. Bus travel time prediction based on dynamic model [J]. Computer Engineering and Applications, 2016, 52(3): 103-107.
[10]	ZHANG Mingguang, ZHANG Yu. Distribution network state estimation based on artificial neural network for pseudo measurement modeling [J]. Computer Engineering and Applications, 2016, 52(17): 253-256.
[11]	CHEN Xianfu, LI Shijun, ZENG Hui. Classification of web pages based on extreme learning machine [J]. Computer Engineering and Applications, 2015, 51(5): 102-106.
[12]	PENG Lirong1, ZHOU Lei2. Fusion of DM with cognitive and behavior calculating models for improving teaching quality [J]. Computer Engineering and Applications, 2014, 50(9): 237-241.
[13]	PAN Weizhou, CHEN Zhenzhou, LI Xingmin. Decryption method of Baidu map’s coordinates based on artificial neural network [J]. Computer Engineering and Applications, 2014, 50(17): 110-113.
[14]	YU Anlei, PI Dechang. Software defect prediction model based on PSO-BP [J]. Computer Engineering and Applications, 2013, 49(7): 64-67.
[15]	MO Lianguang1，2, HONG Yuan2. Application of RS-IPSO-BP Neural Network model for construction engineering cost evaluation [J]. Computer Engineering and Applications, 2013, 49(21): 19-23.

Modified artificial neural network model

一种改进的人工神经网络模型

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics