# What is a self-organising map in Kohonen network?

Kohonen network’s nodes can be in a rectangular (left) or hexagonal (right) topology. A Self-Organising Map, additionally, uses competitive learning as opposed to error-correction learning, to adjust it weights.

Table of Contents

## What is a self-organising map in Kohonen network?

Kohonen network’s nodes can be in a rectangular (left) or hexagonal (right) topology. A Self-Organising Map, additionally, uses competitive learning as opposed to error-correction learning, to adjust it weights.

## What is a self-organizing map (SOM)?

As a basic type of ANNs, let’s consider a self-organizing map (SOM) or self-organizing feature map (SOFM) that is trained using unsupervised learning to produce a low-dimensional, discretized representation of the input space of the training samples, called a map. Self Organizing Map?

**What is a Kohonen network?**

A Kohonen network consists of two layers of processing units called an input layer and an output layer. There are no hidden units.

### Who discovered self-organizing map?

It is discovered by Finnish professor and researcher Dr. Teuvo Kohonen in 1982. The self-organizing map refers to an unsupervised learning model proposed for applications in which maintaining a topology between input and output spaces.

### What is the iteration limit of a Kohonen model?

A Kohonen model with the BMU in yellow, the layers inside the neighbourhood radius in pink and purple, and the nodes outside in blue. n is the iteration limit, i.e. the total number of iterations the network can undergo λ is the time constant, used to decay the radius and learning rate

**How to calculate the Euclidean distance between two nodes in Kohonen network?**

As such, after clustering, each node has its own (i,j) coordinate, which allows one to calculate the Euclidean distance between 2 nodes by means of the Pythagorean theorem. Kohonen network’s nodes can be in a rectangular (left) or hexagonal (right) topology.

## Is it possible to implement self-organizing maps using MATLAB?

Using the above algorithm, a few interesting examples that have mentioned in Self-Organizing Maps Book by Teuvo Kohonen² have been implemented using MATLAB and you can clone it to your local computer as follows: Let’s define the repository’s home as .