Neural network modelling by rank configurations

被引：1

作者：

Bykov, Mykola M. ^{[1
]}

Kovtun, Viacheslav V. ^{[1
]}

Raimy, Abdourahmane ^{[2
]}

Gromaszek, Konrad ^{[3
]}

Smailova, Saule ^{[4
]}

机构：

[1] Vinnytsia Natl Tech Univ, 95 Khmelnytske Shose, UA-21021 Vinnytsia, Ukraine

[2] Univ Cheikh Anta Diop Dakar, UCAD, BP 5005, Dakar, Senegal

[3] Lublin Univ Technol, Ul Nadbystrzycka 38A, PL-20618 Lublin, Poland

[4] East Kazakhstan State Tech Univ, 69 Protozanov St, Ust Kamenogorsk 070004, Kazakhstan

来源：

PHOTONICS APPLICATIONS IN ASTRONOMY, COMMUNICATIONS, INDUSTRY, AND HIGH-ENERGY PHYSICS EXPERIMENTS 2018 | 2018年 / 10808卷

关键词：

rank configurations; modelling; decision making; DRP-codes; neural network; Hopfield net; memcomputer; OPTICAL METHODS; COAL;

D O I：

10.1117/12.2501521

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

The article presents the model of neural network in the form of rank configuration. The neurons are assumed to be the nodes of simplex, which presents a rank configuration, and the weights of the neural network are the edges of this simplex in the proposed model. Edges of simplex are marked by ranks of the weights. This approach allows us to evaluate the adequacy of rank configurations to make decisions on a system that already had proven effective in this application. Also such model gives an opportunity to present neurons as binary codes that preserve ranks of distances (DRP-codes) and to build digital model of memory core of memcomputer. The research of the model is carried out on the process of decimal digits recognition by Hopfield net.

引用

页数：5

共 14 条

[1]

Belongie S, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P454, DOI 10.1109/ICCV.2001.937552

[2]

Bykov M. M., 2014, Patent UA, Patent No. [93719 U, G10L 15/ 00., 93719]

[3]

Bykov M. M., 2013, DETERMINING POTENTIA, V5, P92

[4]

Bykov N. M., 2011, CONT ENG SCI, V4, P187

[5]

Duk M, 2012, PRZ ELEKTROTECHNICZN, V88, P59

[6]

Mashkov V., 2016, IAPGOS, V6, P26

[7] The use of decision tree induction and artificial neural networks for automatic diagnosis of Hashimoto's disease [J].

Omiotek, Z. ;

Burda, A. ;

Wojcik, W. .

EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (16) :6684-6689

[8]

Rovira R., 2015, P SOC PHOTO-OPT INS, V9816, P611

[9]

Sawicki D, 2016, ROCZ OCHR SR, V18, P404

[10]

Smolarz A, 2012, PRZ ELEKTROTECHNICZN, V88, P259

← 1 2 →