Stochastic dynamics and high capacity associative memories

被引：0

作者：

Davey, N ^{[1
]}

Adams, RG ^{[1
]}

机构：

[1] Univ Hertfordshire, Dept Comp Sci, Hatfield AL10 9AB, Herts, England

来源：

ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE | 2002年

关键词：

associative memory; attractor basins; Hopfield neural networks; learning rules; perceptron; performance measures; pseudo-inverse;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The addition of noise to the deterministic Hopfield network, trained with one shot Hebbian learning, is known to bring benefits in the elimination of spurious attractors. This paper extends the analysis to learning rules that have a much higher capacity. The relative energy of desired and spurious attractors is reported and the affect of adding noise to the dynamics is empirically investigated. It is found that the addition of noise brings even more benefit in the case of the higher capacity rules.

引用

页码：1666 / 1670

页数：5

共 50 条

[21] SPARSELY CODED ASSOCIATIVE MEMORIES - CAPACITY AND DYNAMIC PROPERTIES
MEUNIER, C
YANAI, HF
AMARI, S
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1991, 2 (04) : 469 - 487
[22] Exponential recurrent associative memories: Stability and relative capacity
Rajati, Mohammad Reza
Menhaj, Mohammad Bagher
Korjani, Mohammad Mehdi
Dehestani, Alireza
ICTAI-2006: EIGHTEENTH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2006, : 751 - +
[23] ASSOCIATIVE MEMORIES
KRIGMAN, A
INSTRUMENTS & CONTROL SYSTEMS, 1972, 45 (03): : 35 - +
[24] Analysis and Design of Multivalued High-Capacity Associative Memories Based on Delayed Recurrent Neural Networks
Zhang, Jiahui
Zhu, Song
Bao, Gang
Liu, Xiaoyang
Wen, Shiping
IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (12) : 12989 - 13000
[25] MEMORY CAPACITY AND ERROR-TOLERANCE CHARACTERISTICS OF ATTENTIVE ASSOCIATIVE MEMORIES
ATHALE, RA
FRIEDLANDER, CB
STIRK, CW
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1986, 3 (13): : P32 - P32
[26] Complexity preserving increase of the capacity of bidirectional associative memories by dilation and translation
Lenze, B
NEURAL NETWORKS, 1998, 11 (06) : 1041 - 1048
[27] High speed associative memories for feature extraction and visualisation
Raudys, A
PATTERN RECOGNITION LETTERS, 2003, 24 (9-10) : 1317 - 1329
[28] High-Order Associative Memories for Pattern Recognition
Ciocoiu, Iulian B.
NEW ASPECTS OF SYSTEMS, PTS I AND II, 2008, : 509 - +
[29] High performance associative memories and structured weight dilution
Turvey, SP
Hunt, SP
Davey, N
Frank, RJ
APPLICATIONS AND SCIENCE IN SOFT COMPUTING, 2004, : 23 - 30
[30] Synthesization of high-capacity auto-associative memories using complex-valued neural networks
Huang, Yu-Jiao
Wang, Xiao-Yan
Long, Hai-Xia
Yang, Xu-Hua
CHINESE PHYSICS B, 2016, 25 (12)

← 1 2 3 4 5 →