Analysis and design of multivalued many-to-one associative memory driven by external inputs

doi:10.1088/1674-1056/add24b

Abstract This paper proposes a novel multivalued recurrent neural network model driven by external inputs, along with two innovative learning algorithms. By incorporating a multivalued activation function, the proposed model can achieve multivalued many-to-one associative memory, and the newly developed algorithms enable effective storage of many-to-one patterns in the coefficient matrix while maintaining the indispensability of inputs in many-to-one associative memory. The proposed learning algorithm addresses a critical limitation of existing models which fail to ensure completely erroneous outputs when facing partial input missing in many-to-one associative memory tasks. The methodology is rigorously derived through theoretical analysis, incorporating comprehensive verification of both the existence and global exponential stability of equilibrium points. Demonstrative examples are provided in the paper to show the effectiveness of the proposed theory.

Keywords: many-to-one associative memories recurrent neural network global exponential stability external input

Received: 02 April 2025
Revised: 27 April 2025
Accepted manuscript online: 30 April 2025

PACS:	07.05.Mh	(Neural networks, fuzzy logic, artificial intelligence)
	02.30.Ks	(Delay and functional equations)

Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 62376105, 12101208, and 61906072) and the Fundamental Research Funds for the Central Universities (Grant No. 2662022XXQD001).

Corresponding Authors: Hao Zhang
E-mail: hzhang2021@mail.hzau.edu.cn

Cite this article:

Qiang Fang(方强) and Hao Zhang(张浩) Analysis and design of multivalued many-to-one associative memory driven by external inputs 2025 Chin. Phys. B 34 080701

[1] Kohonen T 1972 IEEE Trans. Comput. 100 353
[2] Amari S 1972 IEEE Trans. Comput. 100 1197
[3] Hopfield J J 1982 Proc. Natl. Acad. Sci. USA 79 2554
[4] Simas R, Sa-Couto L andWichert A 2023 Neurocomputing 551 126514
[5] Sun J, Han G, Zeng Z and Wang Y 2019 IEEE Trans. Cybern. 50 2935
[6] Hu S G, Liu Y, Liu Z, Chen T P, Wang J J, Yu Q and Hosaka S 2015 Nat. Commun. 6 7522
[7] Liu X, Zeng Z and Wen S 2016 IEEE Trans. Circuits. Syst. 63 1454
[8] Chen X, Song Q and Li Z 2017 IEEE Trans. Syst. Man Cybern. 48 2305
[9] Kosko B 1988 IEEE Trans. Syst. Man Cybern. 18 49
[10] Hagiwara M 1990 Proceedings of the International Joint Conference on Neural Networks 1 3
[11] Park J, Kim H Y, Park Y and Lee S W 2001 Neural Netw. 14 107
[12] Liu D and Lu Z 1997 IEEE Trans. Neural Netw. 8 1468
[13] Li F, Li A Q, Gan Q D and Ma H Y 2024 Chin. Phys. B 33 040307
[14] Shao X G, Zhang J and Lu Y J 2024 Chin. Phys. B 33 070203
[15] Lu J L, et al. 2025 Chin. Phys. B 34 018703
[16] Xi Y G, Yu Y G, Zhang S and Hai X D 2018 Chin. Phys. B 27 010202
[17] Qi A X, Zhu B D and Wang G Y 2022 Chin. Phys. B 31 020502
[18] Zeng Z G and Wang J 2007 Neural Comput. 19 2149
[19] Michel A N, Farrell J A and Sun H F 1990 IEEE Trans. Circuits. Syst. 37 1356
[20] Lu Z and Liu D 1998 IEEE Trans Circuits Syst 45 1601
[21] Grassi G 1997 IEEE Trans. Circuits. Syst. 44 835
[22] Zeng Z G and Wang J 2008 IEEE Trans. Syst. Man Cybern. 38 1525
[23] Sha C and Zhao H 2017 Neurocomputing 266 433
[24] Zhang H, Huang Y, Wang B and Wang Z 2014 Neurocomputing 136 337
[25] Shang Y 2015 Math. Probl. Eng. 2015 1
[26] Zhou C, Zeng X, Yu J and Jiang H 2016 Neurocomputing 186 44
[27] Huang Y J, Wang X Y, Long H X and Yang X H 2016 Chin. Phys. B 25 120701
[28] Zhang J, Zhu S, Bao G, Liu X and Wen S 2021 IEEE Trans. Cybern. 52 12989
[29] Nie X B and Zheng W X 2016 IEEE Trans. Neural Netw. Learn. Syst. 46 679
[30] Guo Z Y, Liu L L and Wang J 2019 IEEE Trans. Neural Netw. Learn. Syst. 30 2052
[31] Guo Z Y, Liu L L and Wang J 2020 IEEE Trans. Syst. Man Cybern. 50 4458
[32] Johnson M and Chartier S 2014 Proceedings of the International Conference on Artificial General Intelligence 1 53
[33] Hattori M and Hagiwara M 1998 Neurocomputing 19 99
[34] Li Y, Li J, Duan S, Wang L and Guo M 2021 Neurocomputing 454 382
[35] Yano Y and Osana Y 2009 Proceedings of the International Conference on Artificial General Intelligence 43 3444
[36] Sudo A, Sato A and Hasegawa O 2007 Proceedings of the International Conference on Artificial General Intelligence 11 619
[37] Shen F, Ouyang Q, Ksai W and Hasegawa O 2013 Neurocomputing 104 57
[38] Masuyama N, Loo C K, SeeraMand Kubota N 2018 IEEE Trans. Neural Netw. Learn. Syst. 29 1058
[39] Du S, Zhang Z, Li J, Sun C, Sun J and Hong Q 2023 IEEE Trans. Biomed Circuits. Syst. 17 433
[40] Zhang Y, Lv J and Zeng Z 2022 IEEE Trans. Cybern. 53 7844
[41] Wang W, Sun Y, Yuan M, Wang Z, Cheng J, Fan D and Wang C 2021 Chaos Soliton. Fract. 150 111110
[42] Wang S, Gao M, Wu H, Luo F, Jiang F and Tao L 2024 Appl. Soft Comput. 167 112381

[1]	Recurrent neural network decoding of rotated surface codes based on distributed strategy Fan Li(李帆), Ao-Qing Li(李熬庆), Qi-Di Gan(甘启迪), and Hong-Yang Ma(马鸿洋). Chin. Phys. B, 2024, 33(4): 040307.
[2]	Coexistence and local Mittag-Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions Yu-Jiao Huang(黄玉娇), Shi-Jun Chen(陈时俊), Xu-Hua Yang(杨旭华), Jie Xiao(肖杰). Chin. Phys. B, 2019, 28(4): 040701.
[3]	Synthesization of high-capacity auto-associative memories using complex-valued neural networks Yu-Jiao Huang(黄玉娇), Xiao-Yan Wang(汪晓妍), Hai-Xia Long(龙海霞), Xu-Hua Yang(杨旭华). Chin. Phys. B, 2016, 25(12): 120701.
[4]	Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions Huang Yu-Jiao (黄玉娇), Hu Hai-Gen (胡海根). Chin. Phys. B, 2015, 24(12): 120701.
[5]	Stability and attractive basins of multiple equilibria in delayed two-neuron networks Huang Yu-Jiao(黄玉娇), Zhang Hua-Guang(张化光), and Wang Zhan-Shan(王占山) . Chin. Phys. B, 2012, 21(7): 070701.
[6]	Chaotic diagonal recurrent neural network Wang Xing-Yuan(王兴元) and Zhang Yi(张诣) . Chin. Phys. B, 2012, 21(3): 038703.
[7]	Novel delay-distribution-dependent stability analysis for continuous-time recurrent neural networks with stochastic delay Wang Shen-Quan (王申全), Feng Jian (冯健), Zhao Qing (赵青). Chin. Phys. B, 2012, 21(12): 120701.
[8]	Robust stability analysis of Takagi–Sugeno uncertain stochastic fuzzy recurrent neural networks with mixed time-varying delays M. Syed Ali . Chin. Phys. B, 2011, 20(8): 080201.
[9]	Global exponential stability of mixed discrete and distributively delayed cellular neural network Yao Hong-Xing(姚洪兴) and Zhou Jia-Yan(周佳燕). Chin. Phys. B, 2011, 20(1): 010701.
[10]	Improved delay-dependent globally asymptotic stability of delayed uncertain recurrent neural networks with Markovian jumping parameters Ji Yan(籍艳) and Cui Bao-Tong(崔宝同). Chin. Phys. B, 2010, 19(6): 060512.
[11]	New results on global exponential stability of competitive neural networks with different time scales and time-varying delays Cui Bao-Tong(崔宝同), Chen Jun(陈君), and Lou Xu-Yang(楼旭阳). Chin. Phys. B, 2008, 17(5): 1670-1677.
[12]	Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network Ma Qian-Li(马千里), Zheng Qi-Lun(郑启伦), Peng Hong(彭宏), Zhong Tan-Wei(钟谭卫), and Qin Jiang-Wei(覃姜维) . Chin. Phys. B, 2008, 17(2): 536-542.
[13]	Synchronization of an uncertain chaotic system via recurrent neural networks Tan Wen (谭文), Wang Yao-Nan (王耀南). Chin. Phys. B, 2005, 14(1): 72-76.
[14]	Analysis of global exponential stability for a class of bi-directional associative memory networks Wang Hong-Xia (王宏霞), He Chen (何晨). Chin. Phys. B, 2003, 12(3): 259-263.
[15]	Global exponential convergence analysis of delayed cellular neural networks Zhang Qiang (张强), Ma Run-Nian (马润年), Wang Chao (王超), Xu Jin (许进). Chin. Phys. B, 2003, 12(1): 22-24.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Analysis and design of multivalued many-to-one associative memory driven by external inputs

Cite this article:

Online attention