continuous neural networks
Recently Published Documents


TOTAL DOCUMENTS

38
(FIVE YEARS 1)

H-INDEX

7
(FIVE YEARS 0)

2021 ◽  
Vol 38 (1) ◽  
pp. 207-213
Author(s):  
Süleyman Burçin Şüyun ◽  
Şakir Taşdemir ◽  
Serkan Biliş ◽  
Alexandru Milea

Range throughout Turkey in this paper, the author trained the continuous neural networks, and used a total of 4,000 fundus images, including images with different degrees of fundus disorders and images without disorders, so that CNN can detect whether the patient has hypertension and arteriosclerosis according to macular degeneration in the fundus images. In order to obtain more effective results from the deep learning structure using convolutional neural network, this paper prepared more data sets on the basis of Turkey, combined with the local data sets to educate the deep learning model, so as to integrate the data globally, which can help standardize the results and improve the accuracy. The system is used to diagnose retinal vascular degeneration, such as fundus vascular disease and macular edema disease. Based on this basic understanding, the research has been used for the detection and classification of hypertensive retinopathy that has similar causes. The author also points out the limitations of the system. Among them, the most important limitation is the need for long-term financial sustainability.



2017 ◽  
Vol 31 (2) ◽  
pp. 363-375 ◽  
Author(s):  
Mariel Alfaro-Ponce ◽  
Isaac Chairez ◽  
Ralph Etienne-Cummings






2016 ◽  
Vol 197 ◽  
pp. 205-211 ◽  
Author(s):  
Fan Yang ◽  
Hongli Dong ◽  
Zidong Wang ◽  
Weijian Ren ◽  
Fuad E. Alsaadi




2014 ◽  
Vol 25 (8) ◽  
pp. 1583-1587 ◽  
Author(s):  
Abdolreza Joghataie ◽  
Omid Oliyan Torghabehi






2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Hongjun Yu ◽  
Xiaozhan Yang ◽  
Chunfeng Wu ◽  
Qingshuang Zeng

This paper is concerned with global stability analysis for a class of continuous neural networks with time-varying delay. The lower and upper bounds of the delay and the upper bound of its first derivative are assumed to be known. By introducing a novel Lyapunov-Krasovskii functional, some delay-dependent stability criteria are derived in terms of linear matrix inequality, which guarantee the considered neural networks to be globally stable. When estimating the derivative of the LKF, instead of applying Jensen’s inequality directly, a substep is taken, and a slack variable is introduced by reciprocally convex combination approach, and as a result, conservatism reduction is proved to be more obvious than the available literature. Numerical examples are given to demonstrate the effectiveness and merits of the proposed method.



Sign in / Sign up

Export Citation Format

Share Document