Modifications of the Givens Training Algorithm for Artificial Neural Networks

被引：2

作者：

Bilski, Jaroslaw ^{[1
]}

Kowalczyk, Bartosz ^{[1
]}

Cader, Andrzej ^{[2
,3
]}

机构：

[1] Czestochowa Tech Univ, Inst Computat Intelligence, Czestochowa, Poland

[2] Univ Social Sci, Informat Technol Inst, Lodz, Poland

[3] Clark Univ, Worcester, MA 01610 USA

来源：

ARTIFICIAL INTELLIGENCEAND SOFT COMPUTING, PT I | 2019年 / 11508卷

关键词：

Feed-forward neural network; Training algorithm; Optimization; QR decomposition; Givens rotation; Training acceleration; FEATURES;

D O I：

10.1007/978-3-030-20912-4_2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Givens algorithm is a supervised training method for neural networks. This paper presents several optimization techniques that could be applied on the top of the Givens algorithm. First, the classic variant of the Givens method is briefly described. The main section of the article contains a detailed description of the proposed retry worst samples, skip best samples, and the Givens epoch update optimization techniques. The paper concludes with the simulation results and an overall summary.

引用

页码：14 / 28

页数：15

共 25 条

[1] N-VALUED REFINED NEUTROSOPHIC SOFT SETS AND THEIR APPLICATIONS IN DECISION MAKING PROBLEMS AND MEDICAL DIAGNOSIS [J].

Alkhazaleh, Shawkat ;

Hazaymeh, Ayman A. .

JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH, 2018, 8 (01) :79-86

[2] The Parallel Modification to the Levenberg-Marquardt Algorithm [J].

Bilski, Jaroslaw ;

Kowalczyk, Bartosz ;

Grzanek, Konrad .

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2018, PT I, 2018, 10841 :15-24

[3] Parallel Levenberg-Marquardt Algorithm Without Error Backpropagation [J].

Bilski, Jaroslaw ;

Wilamowski, Bogdan M. .

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2017, PT I, 2017, 10245 :25-39

[4] Application of the Givens Rotations in the Neural Network Learning Algorithm [J].

Bilski, Jaroslaw ;

Kowalczyk, Bartosz ;

Zurada, Jacek M. .

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2016, 2016, 9692 :46-56

[5] Parallel Approach to the Levenberg-Marquardt Learning Algorithm for Feedforward Neural Networks [J].

Bilski, Jaroslaw ;

Smolag, Jacek ;

Zurada, Jacek M. .

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, PT I, 2015, 9119 :3-14

[6] The Parallel Approach to the Conjugate Gradient Learning Algorithm for the Feedforward Neural Networks [J].

Bilski, Jaroslaw ;

Smolag, Jacek ;

Galushkin, Alexander I. .

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING ICAISC 2014, PT I, 2014, 8467 :12-21

[7] TEXTURE AND GENE EXPRESSION ANALYSIS OF THE MRI BRAIN IN DETECTION OF ALZHEIMER'S DISEASE [J].

Bustamam, Alhadi ;

Sarwinda, Devvi ;

Ardenaswari, Gianinna .

JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH, 2018, 8 (02) :111-120

[8]

Chang O, 2017, J ARTIF INTELL SOFT, V7, P125, DOI 10.1515/jaiscr-2017-0009

[9] DEEP FEATURES EXTRACTION FOR ROBUST FINGERPRINT SPOOFING ATTACK DETECTION [J].

de Souza, Gustavo Botelho ;

da Silva Santos, Daniel Felipe ;

Pires, Rafael Goncalves ;

Marana, Aparecido Nilceu ;

Papa, Joao Paulo .

JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH, 2019, 9 (01) :41-49

[10]

Gabryel M, 2018, J UNIVERS COMPUT SCI, V24, P357

← 1 2 3 →