A scalable multi-signal approach for the parallelization of self-organizing neural networks
Abstract Self-Organizing Neural Networks (SONNs) have a wide range of applications with
massive computational requirements that often need to be satisfied with optimized parallel …
massive computational requirements that often need to be satisfied with optimized parallel …
Asymmetric -Means Clustering of the Asymmetric Self-Organizing Map
D Olszewski - Neural Processing Letters, 2016 - Springer
An asymmetric approach to clustering of the asymmetric self-organizing map is proposed.
The clustering is performed using an improved asymmetric version of the well-known k k …
The clustering is performed using an improved asymmetric version of the well-known k k …
Image inpainting based on self-organizing maps by using multi-agent implementation
M Favorskaya, LC Jain, A Bolgov - Procedia Computer Science, 2014 - Elsevier
The image inpainting is a well-known task of visual editing. However, the efficiency strongly
depends on sizes and textural neighborhood of “missing” area. Various methods of image …
depends on sizes and textural neighborhood of “missing” area. Various methods of image …
Advances in computational intelligence
I Rojas, JCI Moncusi, G Joya - Soft Computing, 2013 - Springer
In the present issue of Soft-Computing, it is a pleasure to present you a selection of 11
extended versions of selected papers from the eleventh edition of the International Work …
extended versions of selected papers from the eleventh edition of the International Work …
Octupolar approximation for the excluded volume of axially symmetric convex bodies
We propose a simply computable formula for the excluded volume of convex, axially
symmetric bodies, based on the classical Brunn-Minkoski theory for convex bodies, which is …
symmetric bodies, based on the classical Brunn-Minkoski theory for convex bodies, which is …
Image and geometry processing with oriented and scalable map
H Hua - Neural Networks, 2016 - Elsevier
We turn the Self-organizing Map (SOM) into an Oriented and Scalable Map (OS-Map) by
generalizing the neighborhood function and the winner selection. The homogeneous …
generalizing the neighborhood function and the winner selection. The homogeneous …
Explicit excluded volume of cylindrically symmetric convex bodies
We represent explicitly the excluded volume V e {B 1, B 2} of two generic cylindrically
symmetric, convex rigid bodies, B 1 and B 2, in terms of a family of shape functionals …
symmetric, convex rigid bodies, B 1 and B 2, in terms of a family of shape functionals …
A multi-signal variant for the gpu-based parallelization of growing self-organizing networks
Among the many possible approaches for the parallelization of self-organizing networks,
and in particular of growing self-organizing networks, perhaps the most common one is …
and in particular of growing self-organizing networks, perhaps the most common one is …
An improved adaptive self-organizing map
D Olszewski, J Kacprzyk, S Zadrożny - Challenging Problems and …, 2016 - Springer
We propose a novel adaptive Self-Organizing Map (SOM). In the introduced approach, the
SOM neurons' neighborhood widths are computed adaptively using the information about …
SOM neurons' neighborhood widths are computed adaptively using the information about …
[HTML][HTML] Towards a 3D modeling of brain tumors by using endoneurosonography and neural networks
Minimally invasive surgeries have become popular because they reduce the typical risks of
traditional interventions. In neurosurgery, recent trends suggest the combined use of …
traditional interventions. In neurosurgery, recent trends suggest the combined use of …