Question I: Develop a classifier that divides the interval between $0$ and $1$ into five classes using SOM network.

Use MATLAB to generate $100$ values in the interval specified with a uniform distribution. Use these values as inputs for the SOM.

Now square each number so that the distribution is no longer uniform. Use these values as inputs for the SOM.

How are the weights of the SOM distributed?

Is there some relationship between how the weights are distributed and how the squared input values are distributed?