The Kohonen Self-Organizing Mapis named after the researcher Dr. Teuvo Kohonen.
A Kohonen Self-Organizing Map is a map that is used for maintaining neighbor topology. It is referred to as a neural network that is trained by competitive learning.
Bellow are the two most used topologies in the Kohonen Self-Organizing Map.
The following explains the rectangular grid topology:
There is a total difference of nodes between each grid.
The following explains the hexagonal grid topology:
There is a total difference of 8 nodes between each grid.
Each node has its own coordinates after clustering, which can be calculated with the Pythagorean theorem using the Euclidean distance between the two nodes.
A Kohonen Self-Organizing Map is different from common artificial neural networks in its:
A Kohonen Self-Organizing Map consists of a single layer linear 2D grid of neurons. The nodes do not know the values of their neighbors. The weights of links are updated as a function of the given inputs. However, all the nodes on the grid are directly linked to the input vectors.
βij(t)
its radius σ(t)
of BMU in Kohonen Self-Organizing Map.