基于忆阻器的连续学习混沌神经网络

计算机科学 ›› 2013, Vol. 40 ›› Issue (10): 213-217.

基于忆阻器的连续学习混沌神经网络

张椅,段书凯,王丽丹,胡小方

西南大学物理科学与技术学院电子信息工程学院重庆400715;西南大学物理科学与技术学院电子信息工程学院重庆400715;西南大学物理科学与技术学院电子信息工程学院重庆400715;西南大学物理科学与技术学院电子信息工程学院重庆400715

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家自然科学基金(60972155,3,60974020),中央高校基本科研业务费专项资金(XDJK2012A007),重庆市高等学校青年骨干教师资助

Memristor-based Successive Learning Chaotic Neural Network

ZHANG Yi,DUAN Shu-kai,WANG Li-dan and HU Xiao-fang

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 忆阻器具有独特的记忆功能和连续可变的电导状态,在人工智能与神经网络等研究领域具有巨大的应用优势。详细推导了忆阻器的电荷控制模型,将纳米忆阻器与具有智能信息处理能力的混沌神经网络相结合,提出了一种新型的基于忆阻器的连续学习混沌神经网络模型。利用忆阻器可直接实现网络中繁多的反馈与迭代,即完成外部输入对神经元及神经元之间相互作用的时空总和。提出的忆阻连续学习混沌神经网络可以实现对已知模式和未知模式的区分,并能对未知模式进行自动学习和记忆。给出的计算机仿真验证了方案的可行性。由于忆阻器具有纳米级尺寸和自动的记忆能力,该方案有望大大简化混沌神经网络结构。

关键词: 忆阻器,混沌神经网络,连续学习,时空总和

Abstract: With the unique memory ability and continuously variable conductance state,memristors have promising prospects in the fields of artificial intelligence and artificial neural network．This paper derived the charge-controlled memristor model in detail．Combining the nanometer memristor and chaotic neural network,a novel type of memristor-based successive learning chaotic neural network model was proposed．The numerous feedbacks and iterative in the network,that is,the spatio-temporal summation of external input to neurons and the interaction between neurons,can been achieved by taking advantage of memristor．In the proposed model,it makes use of the difference in the response to the input patterns to distinguish the unknown pattern from the stored known patterns．When an input pattern is regarded as an unknown pattern,it will be memorized in the network．The effectiveness was verified through the given simulation experiments．With the memristor’s nano-scale size and automatic memory capacity,the program is expected to greatly simplify the structure of chaotic neural network.

Key words: Memristor,Chaotic neural network,Successive learning,Spatio-temporal summation

张椅,段书凯,王丽丹,胡小方. 基于忆阻器的连续学习混沌神经网络[J]. 计算机科学, 2013, 40(10): 213-217. https://doi.org/

ZHANG Yi,DUAN Shu-kai,WANG Li-dan and HU Xiao-fang. Memristor-based Successive Learning Chaotic Neural Network[J]. Computer Science, 2013, 40(10): 213-217. https://doi.org/

参考文献

[1] Liu Guang-yuan,Duan Shu-kai．A Chaotic Neural Network and its Applications in Separation of Superimposed Pattern and Many-to-Many Associative Memory[J]．Computer Science,2003,0:83-85
[2] Aihara K,Takabe T,Toyoda M．Chaotic Neural Networks[J]．Physics Letters A,1990,144(6/7):333-340
[3] Yao Y,Freeman W J．Model of Biological Pattern Recognitionwith Spatially Chaotic Dynamics Neural Networks[J]．Neural Networks,1990,3:153-170
[4] Osana Y,Hagiwara M．Separation of Superimposed Pattern and Many-to-Many Associations by Chaotic Neural Networks[J]．IEEE International Joint Conference on Neural Networks Proceedings,1998,1:514-519
[5] Kaneko K,Clustering,Coding,et al．Hierararchial Ordering and Control in a Network of Chaotic Elements[J]．Physics Letters D,1990,41:137-172
[6] Ishii S,Fukumizu K,Watanabe S．A Network of Chaotic Ele-ments for Information Processing[J]．Neural Networks,1996,1:25-40
[7] Osana Y,Hattori M,Hagiwara M．Chaotic Bidirectional Associa-tive Memory[C]∥International Conference on Neural Networks．Houston,1997,2:816-821
[8] Osana Y,Hagiwara M．Successive Learning in Chaotic NeuralNetwork[J]．IEEE International Joint Conference on Neural Networks Proceedings,Anchorage,1998,2:1510-1515
[9] Kawasaki N,Osana Y,Hagiwara M．Chaotic associative memory for successive learning using internal patterns[J]．IEEE International Conference on Systems,Man,and Cybernetics,2000,4:2521-2526
[10] Osana Y．Improved chaotic associative memory using distributed patterns for image retrieval[C]∥Proceedings of the InternationalJoint Conference on Neural Networks．2003,2:846-851
[11] Liu G Y,Duan S K．A Chaotic Neural Network and its Applications in Separation Superimposed Pattern and Many-to-Many Associative Memory[C]∥Computer Science．Chongqing,China,2003,30:83-85
[12] Duan S K,Liu G Y,Wang L D,et al.A Novel Chaotic Neural Network for Many-to-Many Associations and Successive Lear-ning[C]∥IEEE International Conference on Neural Networks and Signal Processing．Nanjing,China,2003,1:135-138
[13] Duan S K,Wang L D．A Novel Chaotic Neural Network for Automatic Material Ratio System[C]∥International Symposium on Neural Networks．Lecture Notes in Computer Science,Dalian,China,2004:813-819
[14] Wang Li-dan,Duan Shu-kai,Liu Guang-yuan．Adaptive chaotic controlling method of a chaotic neural network model[J]．Lecture Notes in Computer Science,2005,3496:363-368
[15] Chua L O．Memristor-the missing circuit element[J]．IEEETrans Circuit Theory,1971,8:507-519
[16] Chua L O,Kang S K．Memristive devices and systems[J]．P IEEE,1976,4:209-223
[17] Strukov D B,Snider G S,Stewart D R,et al．The missing memristor found[J]．Nature,2008,3:80-83
[18] Hu Xiao-fang,Duan Shu-kai,Wang Li-dan,et al．MemristiveCrossbar Array with Application in Image Processing[J]．Science China Information Sciences,2012,5(2):461-462
[19] Hu Xiao-fang,Duan Shu-kai,Wang Li-dan,et al．Analog Memory Based on Pulse Controlled Memristor[J]．Journal of University of Electronic Science and Technology of China,2011,0:643-647
[20] Gao Shi-yong,Duan Shu-kai,Wang Li-dan．Memristive CellNeural Network(CNN)with Applications in Image Processing[J]．Journal of Southwest University:Natural Science Edition,2011,33(11):63-70
[21] Sah M P,Yang Chang-ju,Kim H,et al.A Voltage Mode Memristor Bridge Synaptic Circuit with Memristor Emulators[J]．Sensors,2012,2:3587-3604
[22] Kim H,Yang Chang-ju,Chua L O R T．Neural Synaptic Weighting With a Pulse-Based Memristor Circuit[J]．IEEE Transaction on Circuits and System I,2012,9:148-158
[23] Al-Sarawi S K O,Cho K-R,Kim S-J,et al．Memristor-based syna-ptic networks and logical operations using in-situ computing[J]．IEEE,2011:137-142
[24] Yao Yong,Freeman W J．Model of biological pattern recognitionwith spatially chaotic dynamics[J]．Neural Networks,1990,3:153-170
[25] Duan Shua-kai,Liu Guang-yuan．Parameters Effecting on Pr-operties of Chaotic Associative Memory[J]．Signal Processing,2003,9:245-248

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed