Method for Reducing Neural-Network Models of Computer Vision

被引：1

作者：

Kroshchanka, A. A. ^{[1
]}

Golovko, V. A. ^{[1
,2
]}

Chodyka, M. ^{[2
]}

机构：

[1] Brest State Tech Univ Educ Estab, Ul Moskovskaya 267, Brest 224017, BELARUS

[2] Akad Bialska Nauk Stosowanych Jana Pawla II, Sidorska Ul 95-97,P 271R, PL-21500 Biala Podlaska, Poland

来源：

PATTERN RECOGNITION AND IMAGE ANALYSIS | 2022年 / 32卷 / 02期

关键词：

deep neural networks; reduction of neural network parameters; pretraining of deep neural networks; computer vision; ALGORITHM;

D O I：

10.1134/S1054661822020146

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This article proposes an approach to reducing fully connected neural networks using classical and modified pretraining of deep neural networks. The authors have demonstrated that this approach can significantly reduce the number of parameters of the trained neural network with little or no reduction in the generalizing ability. The capabilities of the proposed method are demonstrated on classical computer vision datasets.

引用

页码：294 / 300

页数：7

共 13 条

[1] Bozinovski Stevo, 1976, Proceedings of Symposium Informatica, P121
[2] Chai C. W., 2018, ARXIV180902209 CSLG
[3] Golovko V., 2016, Optical Memory and Neural Networks 2016 25:3, V25, P127, DOI [DOI 10.3103/S1060992X16030073, 10.3103/S1060992X16030073]
[4] Golovko V.A, 2015, LECT NEUROINFORMATIC
[5] Golovko V, 2015, INT WORKSH INT DATA, P182, DOI 10.1109/IDAACS.2015.7340725
[6] THE WAKE-SLEEP ALGORITHM FOR UNSUPERVISED NEURAL NETWORKS
HINTON, GE
DAYAN, P
FREY, BJ
NEAL, RM
[J]. SCIENCE, 1995, 268 (5214) : 1158 - 1161
[7] A fast learning algorithm for deep belief nets
Hinton, Geoffrey E.
Osindero, Simon
Teh, Yee-Whye
[J]. NEURAL COMPUTATION, 2006, 18 (07) : 1527 - 1554
[8] Krizhevsky A., 2009, Technical report, P1
[9] The Reduction of Fully Connected Neural Network Parameters Using the Pre-training Technique
Kroshchanka, Aliaksandr
Golovko, Vladimir
[J]. PROCEEDINGS OF THE 11TH IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS: TECHNOLOGY AND APPLICATIONS (IDAACS'2021), VOL 2, 2021, : 937 - 941
[10] Reducing Parameters of Neural Networks via Recursive Tensor Approximation
Kwon, Kyuahn
Chung, Jaeyong
[J]. ELECTRONICS, 2022, 11 (02)

← 1 2 →