The SOM is a learning algorithm introduced by the Finnish professor Teuvo Kohonen in the 1980s. It is a computationally convenient abstraction building on work on biologically neural models from the 1970s and morphogenesis models dating back to Alan Turing in the 1950s.
A self-organizing map (SOM) is a type of artificial neural network (ANN) that is trained using unsupervised learning to produce a low-dimensional (typically two-dimensional), discretized representation of the input space of the training samples, called a map. [ ref. ]
We plan to translate the core methods of SOM algorithm, which is elaborated in "MATLAB Implementations and Applications of the Self-Organizing Map", from MATLAB into javascript.
The implementation will be written in javascript/typescript and could be used in modern browsers and node.js application.
You can install som.js via npm
npm install som.js