Improve the Accuracy of Neural Networks using Capsule Layers

被引：0

作者：

Hollosi, Janos ^{[1
]}

Pozna, Claudiu Radu ^{[2
]}

机构：

[1] Szechenyi Istvan Univ, Dept Informat Technol, Gyor, Hungary

[2] Transilvania Univ Brasov, Dept Automat, Brasov, Romania

来源：

2018 18TH IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND INFORMATICS (CINTI) | 2018年

关键词：

neural network; capsule network; dynamic routing; improve accuracy;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Neural networks are a powerful and widely used tools for various classification and segmentation tasks. Nowadays, in the field of computer vision the convolutional neural networks (CNNs) are the most popular solution for many problems. The CNNs performance is looks like exceptionally great when the test images are very close to the training dataset. However if the input images are transformed, such as rotating or tilting, the efficiency of the neural network may be greatly reduced. A new kind of neural network, is called capsule network, is trying to solve this problem. In this paper we examines the efficiency of the capsule network, by trying to increase the accuracy of different networks with capsule layers.

引用

页码：15 / 18

页数：4

共 50 条

[31] Using neural networks to improve simulations in the gray zone
Kriegmair, Raphael
Ruckstuhl, Yvonne
Rasp, Stephan
Craig, George
NONLINEAR PROCESSES IN GEOPHYSICS, 2022, 29 (02) : 171 - 181
[32] Using feature construction to improve the performance of neural networks
Piramuthu, S
Ragavan, H
Shaw, MJ
MANAGEMENT SCIENCE, 1998, 44 (03) : 416 - 430
[33] Using squeeze-and-excitation blocks to improve an accuracy of automatically grading knee osteoarthritis severity using convolutional neural networks
Mikhaylichenko, A. A.
Demyanenko, Y. M.
COMPUTER OPTICS, 2022, 46 (02) : 317 - +
[34] Improving the Accuracy of a Robot by Using Neural Networks (Neural Compensators and Nonlinear Dynamics)
Yan, Zhengjie
Klochkov, Yury
Xi, Lin
ROBOTICS, 2022, 11 (04)
[35] Bridging of layers of neural networks
Kopcanski, D
Odri, S
Petrovacki, D
2002 6TH SEMINAR ON NEURAL NETWORK APPLICATIONS IN ELECTRICAL ENGINEERING, PROCEEDINGS, 2002, : 17 - 22
[36] Deep Neural Networks Using Capsule Networks and Skeleton-Based Attentions for Action Recognition
Ha, Manh-Hung
Chen, Oscal Tzyh-Chiang
IEEE ACCESS, 2021, 9 : 6164 - 6178
[37] Improvement of Vocal Detection Accuracy Using Convolutional Neural Networks
You, Shingchern D.
Liu, Chien-Hung
Lin, Jia-Wei
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2021, 15 (02): : 729 - 748
[38] Increasing the Accuracy of Quantitative Chromatographic Analysis Using Neural Networks
T. Z. Khaburzaniya
A. V. Meshkov
Measurement Techniques, 2014, 57 : 446 - 452
[39] Practical classification accuracy of sequential data using neural networks
Mimura, Mamoru
MACHINE LEARNING WITH APPLICATIONS, 2025, 19
[40] Improving accuracy of Pedestrian Detection using Convolutional Neural Networks
Esfandiari, Neda
Bastanfard, Azam
2020 6TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2020,

← 1 2 3 4 5 →