Kernel Normalised Least Mean Squares with Delayed Model Adaptation

2020 ◽  
Vol 13 (2) ◽  
pp. 1-30
Author(s):  
Nicholas J. Fraser ◽  
Philip H. W. Leong
Keyword(s):  
Model Adaptation ◽  
Least Mean Squares ◽  
Delayed Model

scholarly journals A stochastic time-delayed model for the effectiveness of Moroccan COVID-19 deconfinement strategy

2020 ◽  
Vol 15 ◽  
pp. 50 ◽  
Author(s):  
Houssine Zine ◽  
Adnane Boukhouima ◽  
El Mehdi Lotfi ◽  
Marouane Mahrouf ◽  
Delfim F.M. Torres ◽  
...  
Keyword(s):  
Public Health ◽  
Health Administration ◽  
Policy Makers ◽  
Public Health Administration ◽  
Additional Degree ◽  
Epidemiological Trend ◽  
The Impact ◽  
Near Future ◽  
Stochastic Time ◽  
Delayed Model

Coronavirus disease 2019 (COVID-19) poses a great threat to public health and the economy worldwide. Currently, COVID-19 evolves in many countries to a second stage, characterized by the need for the liberation of the economy and relaxation of the human psychological effects. To this end, numerous countries decided to implement adequate deconfinement strategies. After the first prolongation of the established confinement, Morocco moves to the deconfinement stage on May 20, 2020. The relevant question concerns the impact on the COVID-19 propagation by considering an additional degree of realism related to stochastic noises due to the effectiveness level of the adapted measures. In this paper, we propose a delayed stochastic mathematical model to predict the epidemiological trend of COVID-19 in Morocco after the deconfinement. To ensure the well-posedness of the model, we prove the existence and uniqueness of a positive solution. Based on the large number theorem for martingales, we discuss the extinction of the disease under an appropriate threshold parameter. Moreover, numerical simulations are performed in order to test the efficiency of the deconfinement strategies chosen by the Moroccan authorities to help the policy makers and public health administration to make suitable decisions in the near future.

Bayesian Trigonometric Support Vector Classifier

2003 ◽  
Vol 15 (9) ◽  
pp. 2227-2254 ◽  
Author(s):  
Wei Chu ◽  
S. Sathiya Keerthi ◽  
Chong Jin Ong
Keyword(s):  
Loss Function ◽  
Gaussian Processes ◽  
Likelihood Function ◽  
Support Vector ◽  
Data Sets ◽  
Model Adaptation ◽  
Bayesian Techniques ◽  
Benchmark Data ◽  
Support Vector Classifier ◽  
Set Up

This letter describes Bayesian techniques for support vector classification. In particular, we propose a novel differentiable loss function, called the trigonometric loss function, which has the desirable characteristic of natural normalization in the likelihood function, and then follow standard gaussian processes techniques to set up a Bayesian framework. In this framework, Bayesian inference is used to implement model adaptation, while keeping the merits of support vector classifier, such as sparseness and convex programming. This differs from standard gaussian processes for classification. Moreover, we put forward class probability in making predictions. Experimental results on benchmark data sets indicate the usefulness of this approach.

Sign in / Sign up

Export Citation Format

Share Document