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

[41] An accelerated recurrent network training algorithm
Atiya, A
Parlos, A
IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1101 - 1106
[42] IMAGE SEQUENCE CORRESPONDENCE VIA A HOPFIELD NEURAL-NETWORK
CHANG, JY
LEE, SW
HORNG, MF
OPTICAL ENGINEERING, 1993, 32 (07) : 1531 - 1538
[43] Exact Memory Association in a Simple Hopfield Neural Network with Two Parameters
Cheng, Sui Sun
Chen, Jhien-Shien
SOUTHEAST ASIAN BULLETIN OF MATHEMATICS, 2015, 39 (03) : 321 - 346
[44] DESIGNING THE HOPFIELD NEURAL-NETWORK VIA POLE ASSIGNMENT
CHU, KWE
CHU, E
LI, N
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 1994, 25 (04) : 669 - 681
[45] Associate memory model based on Hopfield neural network with redundant neurons
Nishiyama, Kiyoshi, 1600, (24):
[46] Singular value Decomposition applied to Associative Memory of Hopfield Neural Network
Deb, Tamojay
Ghosh, Anjan K.
Mukherjee, Anjan
MATERIALS TODAY-PROCEEDINGS, 2018, 5 (01) : 2222 - 2228
[47] The Construction of Applied Writing Training Network System
Zhang, Dongxiu
2013 INTERNATIONAL CONFERENCE ON ECONOMIC, BUSINESS MANAGEMENT AND EDUCATION INNOVATION (EBMEI 2013), VOL 18, 2013, 18 : 361 - 364
[48] Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network
Kurikawa, Tomoki
Barak, Omri
Kaneko, Kunihiko
PHYSICAL REVIEW RESEARCH, 2020, 2 (02):
[49] Effects of noise in training patterns on the memory capacity of the fully connected binary Hopfield neural network: Mean-field theory and simulations
Wang, LP
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (04): : 697 - 704
[50] Hopfield neural network model for explaining double dissociation in semantic memory impairment
Shin-ichi Asakawa
Ikuko Kyoya
BMC Neuroscience, 14 (Suppl 1)

← 1 2 3 4 5 →