Self-Organizing Maps is a form of machine learning technique which
employs unsupervised learning. It means that you don’t need to explicitly
tell the SOM about what to learn in the input data. It automatically learns
the patterns in input data and organizes the data into different groups.
I have developed a Python module for SOM. The SOM which I have written
is little different from traditional SOMs because it supports supervised
learning also. It means that when you provide it with a sample set of
inputs and corresponding outputs, it learns to map future unknown inputs
to correct outputs. The code for solving the XOR problem using an SOM
is included in the code.
To read more about SOMs, click to:
Click here to download the source code.