A self-organizing map (SOM) is a type of artificial neural network (ANN) that is trained using unsupervised learning to produce a two-dimensional, discretized representation of the data. It is a method to do dimensionality reduction. Compared to standard clustering alogrithms like k-means, SOMs use a neighborhood function to preserve the topological properties of the input space.
This repository uses the following numpy and numba to develop the SOM and deploy it onto AWS using streamlit.
