Writing to the Hopfield Memory via Training a Recurrent Network

被引：1

作者：

Bao, Han ^{[1
,2
]}

Zhang, Richong ^{[1
,2
]}

Mao, Yongyi ^{[3
]}

Huai, Jinpeng ^{[1
,2
]}

机构：

[1] Beihang Univ, Sch Comp Sci & Engn, SKLSDE, Beijing, Peoples R China

[2] Beihang Univ, Beijing Adv Inst Big Data & Brain Comp, Beijing, Peoples R China

[3] Univ Ottawa, Sch Elect Engn & Comp Sci, Ottawa, ON, Canada

来源：

PRICAI 2019: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II | 2019年 / 11671卷

基金：

中国国家自然科学基金;

关键词：

Hopfield network; Writing protocol; Recurrent network; NEURAL-NETWORKS; CAPACITY;

D O I：

10.1007/978-3-030-29911-8_19

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We consider the problem of writing on a Hopfield network. We cast the problem as a supervised learning problem by observing a simple link between the update equations of Hopfield network and recurrent neural networks. We compare the new writing protocol to existing ones and experimentally verify its effectiveness. Our method not only has a better ability of noise recovery, but also has a bigger capacity compared to the other existing writing protocols.

引用

页码：241 / 254

页数：14

共 50 条

[21] NEURAL NETWORK MODELING OF ASSOCIATIVE MEMORY - BEYOND THE HOPFIELD MODEL
DASGUPTA, C
PHYSICA A, 1992, 186 (1-2): : 49 - 60
[22] The Hopfield associative memory network:: Improving performance with the kernel "trick"
García, C
Moreno, JA
ADVANCES IN ARTIFICIAL INTELLIGENCE - IBERAMIA 2004, 2004, 3315 : 871 - 880
[23] Some Aspects of Associative Memory Construction Based on a Hopfield Network
Karpov, Yu. L.
Karpov, L. E.
Smetanin, Yu. G.
PROGRAMMING AND COMPUTER SOFTWARE, 2020, 46 (05) : 305 - 311
[24] RMBERT: News Recommendation via Recurrent Reasoning Memory Network over BERT
Jia, Qinglin
Li, Jingjie
Zhang, Qi
He, Xiuqiang
Zhu, Jieming
SIGIR '21 - PROCEEDINGS OF THE 44TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2021, : 1773 - 1777
[25] Training a generalized discrete Hopfield network with fuzzy learning rule
Brouwer, RK
1997 IEEE PACIFIC RIM CONFERENCE ON COMMUNICATIONS, COMPUTERS AND SIGNAL PROCESSING, VOLS 1 AND 2: PACRIM 10 YEARS - 1987-1997, 1997, : 794 - 797
[26] A novel memristive Hopfield neural network with application in associative memory
Yang, Jiu
Wang, Lidan
Wang, Yan
Guo, Tengteng
NEUROCOMPUTING, 2017, 227 : 142 - 148
[27] ACCELERATING RECURRENT NEURAL NETWORK TRAINING VIA TWO STAGE CLASSES AND PARALLELIZATION
Huang, Zhiheng
Zweig, Geoffrey
Levit, Michael
Dumoulin, Benoit
Oguz, Barlas
Chang, Shawn
2013 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2013, : 326 - 331
[28] Further results on the asymptotic memory capacity of the generalized Hopfield network
Wu, JW
Ma, JW
Cheng, QS
NEURAL PROCESSING LETTERS, 2004, 20 (01) : 23 - 38
[29] Some Aspects of Associative Memory Construction Based on a Hopfield Network
Yu. L. Karpov
L. E. Karpov
Yu. G. Smetanin
Programming and Computer Software, 2020, 46 : 305 - 311
[30] Associative memory realized by a reconfigurable memristive Hopfield neural network
Hu, S. G.
Liu, Y.
Liu, Z.
Chen, T. P.
Wang, J. J.
Yu, Q.
Deng, L. J.
Yin, Y.
Hosaka, Sumio
NATURE COMMUNICATIONS, 2015, 6

← 1 2 3 4 5 →