How do you access the values of the internal states of networks in the neural network toolbox?

I am trying to access the values of hidden units in MLPs and the distances to all the prototypes in the Self Organizing Map (SOM). I have found the place in the code that they are calculated but the files are read-only so I can't save the values. I haven't found any way to access those values. The SOM is not very useful if you can't get the distances as an output. Right now, the networks produce outputs that are either 0 or 1, the 1 indicating the closest prototype. You can display the values and I suppose I could get them from the display but I'd rather have them as a simple output.

Answer 1

[Greg Heath]

If you use the command

 lookfor som

you will find a listing of som plot routines:

 plotsomhits  - Plot self-organizing map sample hits.
plotsomnc     - Plot Self-organizing map neighbor connections.
plotsomnd     - Plot Self-organizing map neighbor distances.
plotsomplanes - Plot self-organizing map weight planes.
plotsompos    - Plot self-organizing map weight positions.
plotsomtop    - Plot self-organizing map topology.
plotsom       - Plot self-organizing map.

Perhaps you will have more luck looking at their code.

Hope this helps.

*Thank you for formally accepting my answer

Greg