Skip to Content

Self-Organizing Maps Algorithm falls under clustering category.

Self-organizing feature maps (SOMs or SOFMs) are popular neural network method developed by Kohonen as way of representing multidimensional data into lower dimensions usually 2D. This algorithms is un-supervised i.e. it is self learning or self trained.

/wp-content/uploads/2013/01/som_178082.jpg

From SOM tutorial part 1

Training occurs in several steps and over many iterations:

  1. Each node’s weights are initialized.
  2. A vector is chosen at random from the set of training data and presented to the lattice.
  3. Every node is examined to calculate which one’s weights are most like the input vector. The winning node is commonly known as the Best Matching Unit (BMU).
  4. The radius of the neighbourhood of the BMU is now calculated. This is a value that starts large, typically set to the ‘radius’ of the lattice,  but diminishes each time-step. Any nodes found within this radius are deemed to be inside the BMU’s neighbourhood.
  5. Each neighbouring node’s (the nodes found in step 4) weights are adjusted to make them more like the input vector. The closer a node is to the BMU, the more its weights get altered.
  6. Repeat step 2 for N iterations.

som.JPG

Difficult to understand? No worries. Check the below videos in which this algorithm is explained with an actual example in a simple manner.

Further reading with very good examples but very technical articles – http://www.mql5.com/en/articles/283

and http://www.cs.bham.ac.uk/~jxb/NN/l16.pdf [PDF]

and generation5 – Self Organizing Map AI for Pictures

To report this post you need to login first.

1 Comment

You must be Logged on to comment or reply to a post.

  1. kishan kumar

    Hi kamath ,

    can you provide me some datasets in excel or csv format for applying algorithms in Predective analysis as i dont have access to hana.

    Regards,

    Kishan.

    (0) 

Leave a Reply