Global Convergence of FastICA: Theoretical Analysis and Practical Considerations

Author(s):  
Gang Wang ◽  
Xin Xu ◽  
Dewen Hu
2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Muhammad Sulaiman ◽  
Abdellah Salhi ◽  
Asfandyar Khan ◽  
Shakoor Muhammad ◽  
Wali Khan

Plant Propagation Algorithms (PPA) are powerful and flexible solvers for optimisation problems. They are nature-inspired heuristics which can be applied to any optimisation/search problem. There is a growing body of research, mainly experimental, on PPA in the literature. Little, however, has been done on the theoretical front. Given the prominence this algorithm is gaining in terms of performance on benchmark problems as well as practical ones, some theoretical insight into its convergence is needed. The current paper is aimed at fulfilling this by providing a sketch for a global convergence analysis.


2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Abdulkarim Hassan Ibrahim ◽  
Poom Kumam ◽  
Auwal Bala Abubakar ◽  
Jamilu Abubakar

AbstractIn recent times, various algorithms have been incorporated with the inertial extrapolation step to speed up the convergence of the sequence generated by these algorithms. As far as we know, very few results exist regarding algorithms of the inertial derivative-free projection method for solving convex constrained monotone nonlinear equations. In this article, the convergence analysis of a derivative-free iterative algorithm (Liu and Feng in Numer. Algorithms 82(1):245–262, 2019) with an inertial extrapolation step for solving large scale convex constrained monotone nonlinear equations is studied. The proposed method generates a sufficient descent direction at each iteration. Under some mild assumptions, the global convergence of the sequence generated by the proposed method is established. Furthermore, some experimental results are presented to support the theoretical analysis of the proposed method.


Author(s):  
A. Gómez ◽  
P. Schabes-Retchkiman ◽  
M. José-Yacamán ◽  
T. Ocaña

The splitting effect that is observed in microdiffraction pat-terns of small metallic particles in the size range 50-500 Å can be understood using the dynamical theory of electron diffraction for the case of a crystal containing a finite wedge. For the experimental data we refer to part I of this work in these proceedings.


2001 ◽  
Vol 84 (7) ◽  
pp. 27-36
Author(s):  
Aki Yuasa ◽  
Daisuke Itatsu ◽  
Naoki Inagaki ◽  
Nobuyoshi Kikuma

1997 ◽  
Vol 2 (2) ◽  
pp. 118-124
Author(s):  
Geoffrey Hall

Patients who have undergone several sessions of chemotherapy for cancer will sometimes develop anticipatory nausea and vomiting (ANV), these unpleasant side effects occurring as the patients return to the clinic for a further session of treatment. Pavlov's analysis of learning allows that previously neutral cues, such as those that characterize a given place or context, can become associated with events that occur in that context. ANV could thus constitute an example of a conditioned response elicited by the contextual cues of the clinic. In order to investigate this proposal we have begun an experimental analysis of a parallel case in which laboratory rats are given a nausea-inducing treatment in a novel context. We have developed a robust procedure for assessing the acquisition of context aversion in rats given such training, a procedure that shows promise as a possible animal model of ANV. Theoretical analysis of the conditioning processes involved in the formation of context aversions in animals suggests possible behavioral strategies that might be used in the alleviation of ANV, and we report a preliminary experimental test of one of these.


Sign in / Sign up

Export Citation Format

Share Document