Learning neuron model based on non-associative learning mechanism

doi:10.11772/j.issn.1001-9081.2017.08.2229

Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (8): 2229-2233.DOI: 10.11772/j.issn.1001-9081.2017.08.2229

Previous Articles Next Articles

Learning neuron model based on non-associative learning mechanism

BI Song, DIAO Qi, CHAI Xiaofeng, HAN Cunwu

Automation and Field Bus Key Laboratory of Beijing, North China University of Technology, Beijing 100144, China

Received:2017-03-03 Revised:2017-04-17 Online:2017-08-10 Published:2017-08-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61573024),the Beijing Municipal Education and Technology Commission Project (KM201610009001).

基于非联合型学习机制的学习神经元模型

毕松, 刁奇, 柴小丰, 韩存武

北方工业大学现场总线技术及自动化北京市重点实验室, 北京 100144

通讯作者: 刁奇
作者简介:毕松(1983-),男,北京人,副教授,博士,主要研究方向:人工智能、模式识别;刁奇(1993-),女,北京人,硕士研究生,主要研究方向:人工智能、神经网络;柴小丰(1991-),男,河北定州人,硕士研究生,主要研究方向:人工智能、神经网络;韩存武(1961-),男,山东龙口人,教授,博士,主要研究方向:无线通信网络、网络化控制系统。
基金资助:
国家自然科学基金资助项目（61573024）；北京市教科委立项项目（KM201610009001）。

Abstract

Abstract: Biological neurons have non-associative learning mechanisms, and a novel learning neuron with non-associative learning mechanisms was designed, namely learning neuron. Firstly, the simplified description of the habituation learning mechanism and the dishabituation learning mechanism were researched in the non-associative learning mechanisms. Secondly, the mathematical models of habituation and dishabituation learning mechanisms were established. Finally, based on the classical M-P (McCulloch-Pitts) neuron model, the learning neuron model with the ability of habituation and dishabituation learning was proposed. The simulation results verify that the proposed learning neuron has typical habituation and dishabituation learning ability, and provides a good foundation for the construction of new neural network.

Key words: non-associative learning mechanism, learning neuron, habituation, dishabituation

摘要： 针对生物神经细胞所具有的非联合型学习机制，设计了具有非联合型学习机制的新型神经元模型——学习神经元。首先，研究了非联合型学习机制中习惯化学习机制和去习惯化学习机制的简化描述；其次，建立了习惯化和去习惯化学习机制的数学模型；最后，基于经典的M-P（McCulloch-Pitts）神经元模型，提出了具有习惯化和去习惯化学习能力的新型神经元模型——学习神经元。经仿真实验验证，学习神经元具有典型的习惯化和去习惯化学习能力，为构建新型神经网络提供良好的基础。

关键词: 非联合型学习机制, 学习神经元, 习惯化, 去习惯化

CLC Number:

TP183

BI Song, DIAO Qi, CHAI Xiaofeng, HAN Cunwu. Learning neuron model based on non-associative learning mechanism[J]. Journal of Computer Applications, 2017, 37(8): 2229-2233.

毕松, 刁奇, 柴小丰, 韩存武. 基于非联合型学习机制的学习神经元模型[J]. 计算机应用, 2017, 37(8): 2229-2233.

References

[1] SWEAT J D. Mechanisms of Memory[M]. 2版. 北京:科学出版社, 2012:237-289. (SWEAT J D. Mechanisms of Memory[M]. 2nd ed. Beijing:Science Press, 2012:237-289.)
[2] NICHOLLS J G. From Neurons to Brain[M]. 5版. 北京:科学出版社, 2014:428-436. (NICHOLLS J G. From Neurons to Brain[M]. 5th ed. Beijing:Science Press, 2014:428-436.)
[3] GAZZANIGA M S, LVRY R B, MANGUN G R. Cognitive Neuroscience:the Biology of the Mind[M]. 3版. 北京:中国轻工业出版社, 2011:349-356. (GAZZANIGA M S, LVRY R B, MANGUN G R. Cognitive Neuroscience:the Biology of the Mind[M]. 3rd ed. Beijing:Beijing Light Industry Press, 2011:349-356.)
[4] 许少华,何新贵.基于函数正交基展开的过程神经网络学习算法[J].计算机学报,2004,27(5):645-650. (XU S H, HE X G. Learning algorithm of process neural network based on orthogonal function basis expansion[J]. Chinese Journal of Computers, 2004, 27(5):645-650.)
[5] 李大刚,王小艺,刘载文,等.过程神经网络水华预测方法研究[J].计算机与应用化学,2011,28(2):173-176. (LI D G, WANG X Y, LIU Z W, et al. Research water-bloom prediction based on process neural network[J]. Computer and Applied Chemistry, 2011, 28(2):173-176.)
[6] 王兵,李盼池,杨冬黎,等.云过程神经网络模型及算法研究[J].电子与信息学报,2015,37(1):110-115. (WANG B, LI P C, YANG D L, et al. Research on cloud process neural network model and algorithm[J]. Journal of Electronics and Information, 2015, 37(1):110-115.)
[7] 王兵,许少华,孟耀华,等.结构自适应的半监督自组织过程神经网络[J].控制与决策,2015,30(3):507-512. (WANG B, XU S H, MENG Y H, et al. Semi-supervised self-organizing process neural network with self-adaptive structure[J]. Control and Decision, 2015, 30(3):507-512.)
[8] AIZENBERG I. Periodic activation function and a modified learning algorithm for the multivalued neuron[J]. IEEE Transactions on Neuron Networks, 2010, 21(12):1939-1949.
[9] LIU C-Y, CHEN C, CHANG C-T, et al. Single-hidden-layer feed-forward quantum neural network based on Grover learning[J]. Neural Networks, 2013, 45:144-150.
[10] 班晓娟,刘浩,刘卓然.一种基于能量人工神经元模型的自生长、自组织神经网络[J].自动化学报,2011,37(5):615-622. (BAN X J, LIU H, LIU Z R. An energy artificial neuron model based self-growing and self-organizing neural network[J]. Acta Automatica Sinica, 2011, 37(5):615-622.
[11] 钱夔,宋爱国,章华涛,等.基于单胺类神经递质调节发育算法的机器人视觉定位[J].机器人,2014,36(3):362-368. (QIAN K, SONG A G, ZHANG H T, et al. Robot vision location based on developmental algorithm of monoamine neurotransmitters modulation[J]. Robot, 2014, 36(3):362-368.)
[12] MULLER K J, NICHOLLS J G, STENT G S. In Neurobiology of the Leech[M]. New York:Cold Spring Harbor Laboratory, 1981:27-34.
[13] 张爱华,顾建文,郑崇勋.中枢兴奋性传递的突触后电位小波熵分析研究[J].西安交通大学学报,2004,38(4):428-431. (ZHANG A H, GU J W, ZHENG C X. Study on neural excitatory transmission by wavelet entropy analysis of presynaptic potentials[J]. Journal of Xi'an Jiaotong University, 2004, 38(4):428-431.)

[1]	Huaiyu ZHU, Bo LI. Single shot multibox detector recognition method for aerial targets of unmanned aerial vehicle [J]. Journal of Computer Applications, 2021, 41(11): 3234-3241.
[2]	. Semi-supervised representation learning method combining graph autoencoder and clustering [J]. Journal of Computer Applications, 0, (): 0-0.
[3]	. Analysis of complex spam filtering algorithm based on neural network [J]. Journal of Computer Applications, 0, (): 0-0.
[4]	. Recommendation model for user attribute preference modeling based on convolutional neural networks interaction [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	YANG Shuxin, ZHANG Nan. Text sentiment analysis based on sentiment lexicon and context language model [J]. Journal of Computer Applications, 2021, 41(10): 2829-2834.
[6]	WANG Hebing, ZHANG Chunmei. Facial landmark detection based on ResNeXt with asymmetric convolution and squeeze excitation [J]. Journal of Computer Applications, 2021, 41(9): 2741-2747.
[7]	DAI Yurou, YANG Qing, ZHANG Fengli, ZHOU Fan. Trajectory prediction model of social network users based on self-supervised learning [J]. Journal of Computer Applications, 2021, 41(9): 2545-2551.
[8]	. Homologous spectrogram feature fusion with self-attention mechanism for bird sound classification [J]. Journal of Computer Applications, 0, (): 0-0.
[9]	. Review of applications of natural language processing in sentiment analysis [J]. Journal of Computer Applications, 0, (): 0-0.
[10]	. Knowledge graph embedding model based on improved Inception structure [J]. Journal of Computer Applications, 0, (): 0-0.
[11]	CHEN Wei, YANG Yan. Extractive and abstractive summarization model based on pointer networks [J]. Journal of Computer Applications, 0, (): 0-0.
[12]	. Adaptive deep graph convolution using initial residual and decoupling operations [J]. Journal of Computer Applications, 0, (): 0-0.
[13]	ZENG Xiangyin, ZHENG Bochuan, LIU Dan. Detection of left and right railway tracks based on deep convolutional neural network and clustering [J]. Journal of Computer Applications, 2021, 41(8): 2324-2329.
[14]	ZHANG Guohui, LU Xixi, HU Yifan, SUN Jinghe. Machine breakdown rescheduling of flexible job shop based on improved imperialist competitive algorithm [J]. Journal of Computer Applications, 2021, 41(8): 2242-2248.
[15]	DU Yan, LYU Liangfu, JIAO Yichen. Fuzzy prototype network based on fuzzy reasoning [J]. Journal of Computer Applications, 2021, 41(7): 1885-1890.

Learning neuron model based on non-associative learning mechanism

基于非联合型学习机制的学习神经元模型

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics