# Blog

## How many neurons in a Kohonen net? Kohonen networks consist of only two layers. The structure of a typical Kohonen neural network is shown below: As we see, the network consists of two layers: the input layer with four neurons and the output layers with three layers. If you are familiar with neural networks, this structure may look to you like a very simple perceptron.

## How many layers are there in a Kohonen network?

• Kohonen networks consist of only two layers. The structure of a typical Kohonen neural network is shown below: As we see, the network consists of two layers: the input layer with four neurons and the output layers with three layers. If you are familiar with neural networks, this structure may look to you like a very simple perceptron.

## 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 does n mean in 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

## What did Prof Kohonen contribute to artificial neural networks?What did Prof Kohonen contribute to artificial neural networks?

Prof. Kohonen has made many contributions to the field of artificial neural networks, including the Learning Vector Quantization algorithm, fundamental theories of distributed associative memory and optimal associative mappings, the learning subspace method and novel algorithms for symbol processing like redundant hash addressing.  ### How many neurons in a Kohonen net?How many neurons in a Kohonen net?

In a Kohonen net, each neuron of an output layer holds a vector whose dimensionality equals the number of neurons in the input layer (in our case it is four). In turn, the number of neurons in the input layer must be equal to the dimensionality of data points given to the network. We will be working with a four-dimensional data set.

### How many layers are there in a Kohonen network?How many layers are there in a Kohonen network?

Kohonen networks consist of only two layers. The structure of a typical Kohonen neural network is shown below: As we see, the network consists of two layers: the input layer with four neurons and the output layers with three layers. If you are familiar with neural networks, this structure may look to you like a very simple perceptron.

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