Quaternionic multistate Hopfield neural network with extended projection rule

被引：49

作者：

Minemoto, Toshifumi ^{[1
]}

Isokawa, Teijiro ^{[1
]}

Nishimura, Haruhiko ^{[2
]}

Matsui, Nobuyuki ^{[1
]}

机构：

[1] Univ Hyogo, Grad Sch Engn, 2167 Shosha, Himeji, Hyogo 6712280, Japan

[2] Univ Hyogo, Grad Sch Appl Informat, Chuo Ku, Computat Sci Ctr Bldg 5-7F, Kobe, Hyogo 6500047, Japan

来源：

ARTIFICIAL LIFE AND ROBOTICS | 2016年 / 21卷 / 01期

关键词：

Hopfield neural network; Multistate; Projection rule; Quaternion;

D O I：

10.1007/s10015-015-0247-4

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

The aim of this paper is to investigate storing and recalling performances of embedded patterns on associative memory. The associative memory is composed of quaternionic multistate Hopfield neural network. The state of a neuron in the network is described by three kinds of discretized phase with fixed amplitude. These phases are set to discrete values with arbitrary divide size. Hebbian rule and projection rule are used for storing patterns to the network. Recalling performance is evaluated through storing random patterns with changing the divide size of the phases in a neuron. Color images are also embedded and their noise tolerance is explored.

引用

页码：106 / 111

页数：6

共 50 条

[1] Quaternionic Hopfield neural networks with twin-multistate activation function
Kobayashi, Masaki
NEUROCOMPUTING, 2017, 267 : 304 - 310
[2] Associative memory in quaternionic hopfield neural network
Isokawa, Teijiro
Nishimura, Haruhiko
Kamiura, Naotake
Matsui, Nobuyuki
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2008, 18 (02) : 135 - 145
[3] Hybrid Quaternionic Hopfield Neural Network
Kobayashi, Masaki
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2015, E98A (07) : 1512 - 1518
[4] Quaternion Projection Rule for Rotor Hopfield Neural Networks
Kobayashi, Masaki
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (02) : 900 - 908
[5] A Novel Continuous-Valued Quaternionic Hopfield Neural Network
Valle, Marcos Eduardo
2014 BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 2014, : 97 - 102
[6] Projection Rule for Rotor Hopfield Neural Networks
Kitahara, Michimasa
Kobayashi, Masaki
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (07) : 1298 - 1307
[7] Symmetric quaternionic Hopfield neural networks
Kobayashi, Masaki
NEUROCOMPUTING, 2017, 240 : 110 - 114
[8] Rotational Invariance of Quaternionic Hopfield Neural Networks
Kobayashi, Masaki
IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2016, 11 (04) : 516 - 520
[9] Noise Robust Projection Rule for Hyperbolic Hopfield Neural Networks
Kobayashi, Masaki
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (01) : 352 - 356
[10] Three-Dimensional Quaternionic Hopfield Neural Networks
Kobayashi, Masaki
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2017, E100A (07): : 1575 - 1577

← 1 2 3 4 5 →