Dynamic Pattern Recognition Model Based on Neural Network Response to Signal Fluctuation

被引：1

作者：

Doho, Hirotaka ^{[1
]}

Nishimura, Haruhiko ^{[2
]}

Nobukawa, Sou ^{[3
]}

机构：

[1] Kochi Univ, Fac Educ, 2-5-1 Akebono Cho, Kochi 7808520, Japan

[2] Univ Hyogo, Grad Sch Appl Informat, 7-1-28 Minatojima Minami Ho,Chuo Ku, Kobe, Hyogo 6500047, Japan

[3] Chiba Inst Technol, Dept Comp Sci, 2-17-1 Tsudanuma, Narashino, Chiba 2750016, Japan

来源：

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS | 2023年 / 27卷 / 01期

关键词：

neural network; signal fluctuation; pattern recognition; associative memory; input; output correlation;

D O I：

10.20965/jaciii.2023.p0044

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We have proposed a model of dynamic retrieval in as-sociative memory based on temporal input/output cor-relations under a stimulus-response open scheme of neural networks. This mechanism is different from that of the conventional stationary Hopfield model in which the input signal is used only as information for the initial state of the network. Building upon the fun-damental properties of the proposed model, in this pa-per, we newly evaluate the dependence of identifica-tion performance on the signal fluctuation level and on the number of stored patterns by introducing an accuracy rate for known (stored) and unknown (non -stored) patterns, based on the network correlation to the input signal with fluctuation. The results indicate that the dynamic scheme of network response to a fluc-tuating signal leads to increased efficacy and useful-ness.

引用

页码：44 / 53

页数：10

共 22 条

[1] Associative dynamics in a chaotic neural network [J].

Adachi, M ;

Aihara, K .

NEURAL NETWORKS, 1997, 10 (01) :83-98

[2] CHAOTIC NEURAL NETWORKS [J].

AIHARA, K ;

TAKABE, T ;

TOYODA, M .

PHYSICS LETTERS A, 1990, 144 (6-7) :333-340

[3] LEARNING OF CORRELATED PATTERNS IN SPIN-GLASS NETWORKS BY LOCAL LEARNING RULES [J].

DIEDERICH, S ;

OPPER, M .

PHYSICAL REVIEW LETTERS, 1987, 58 (09) :949-952

[4]

Doho H., 2008, PROC 18 FUZZY ARTIFI, P491

[5]

Gerstner W, 2014, NEURONAL DYNAMICS: FROM SINGLE NEURONS TO NETWORKS AND MODELS OF COGNITION, P1, DOI 10.1017/CBO9781107447615

[6]

Haykin S., 1994, Neural networks: A comprehensive foundation

[7] Associative memory model with long-tail-distributed Hebbian synaptic connections [J].

Hiratani, Naoki ;

Teramae, Jun-Nosuke ;

Fukai, Tomoki .

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2013, 6

[8] NEURONS WITH GRADED RESPONSE HAVE COLLECTIVE COMPUTATIONAL PROPERTIES LIKE THOSE OF 2-STATE NEURONS [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1984, 81 (10) :3088-3092

[9] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558

[10] Stochastic Resonance in Recurrent Neural Network with Hopfield-Type Memory [J].

Katada, Naofumi ;

Nishimura, Haruhiko .

NEURAL PROCESSING LETTERS, 2009, 30 (02) :145-154

← 1 2 3 →