Self-organized maps (SOM), sometimes known as Kohonen networks or Winner take all units (WTU), are a very special kind of neural network, motivated by a distinctive feature of the human brain. In our brain, different sensory inputs are represented in a topologically ordered manner. Unlike other neural networks, neurons are not all connected to each other via weights, instead, they influence each other's learning. The most important aspect of SOM is that neurons represent the learned inputs in a topographic manner.

In SOM, neurons are usually placed at nodes of a (1D or 2D) lattice. Higher dimensions are also possible but are rarely used in practice. Each neuron in the lattice is connected to all the input units via weight matrix. Here, you can see a SOM with 3 x 4 (12 neurons) and seven inputs. For clarity, only the weight vectors connecting all inputs to one neuron are shown. In this case, each neuron will have seven elements, resulting in a combined weight matrix of size (12 x 7):

SOM learns via competitive learning. It can be considered as a nonlinear generalization of PCA and thus, like PCA, can be employed for dimensionality reduction.