What Does Self-Organizing Map Mean?
A self-organizing map (SOM) is a type of artificial neural network that uses unsupervised learning to build a two-dimensional map of a problem space. The key difference between a self-organizing map and other approaches to problem solving is that a self-organizing map uses competitive learning rather than error-correction learning such as backpropagation with gradient descent.
A self-organizing map can generate a visual representation of data on a hexagonal or rectangular grid. Applications include meteorology, oceanography, project prioritization, and oil and gas exploration.
A self-organizing map is also known as a self-organizing feature map (SOFM) or a Kohonen map.
Techopedia Explains Self-Organizing Map
A self-organizing map is a type of artificial neural network that attempts to build a two-dimensional map of some problem space. The problem space can be anything from votes in U.S. Congress, maps of colors and even links between Wikipedia articles.
The goal is to attempt to mirror the way the visual cortex in the human brain sees objects using signals generated by the optic nerves. The aim is to make all the nodes in the network respond differently to different inputs. A self-organizing map makes use of competitive learning where the nodes eventually specialize.
When fed input data, the Euclidean distance, or the straight-line distance between the nodes, which are given a weight, is computed. The node in the network that is most similar to the input data is called the best matching unit (BMU).
As the neural network moves through the problem set, the weights start to look more like the actual data. The neural network has thus trained itself to see patterns in the data much the way a human sees.
The approach differs from other AI techniques such as supervised learning or error-correction learning, but without using error or reward signals to train an algorithm. Thus, a self-organizing map is a kind of unsupervised learning.