MATLAB: Iteration determine in Self-Organizing Map to Cluster Data

Deep Learning Toolboxneural network

in the attach i share an example of Self-Organizing Map that provided by MATLAB my problem is that the iteration number is fixed in 200. change it with other value like 150, 100, 500..

Regards

Best Answer

Type, without ending semicolon

 net = net

then all properties will be displayed.

Chose the one that corresponds to iteration number.

Then change it.

Something along the lines of

 net.property.iteration number = 100.

to change 200 to 100.

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: When I am the training a elman neural network it is working only with 5 or lower no. of hidden layers, as I tried to increase no of layers its giving only 50% accuracy which means network is not trained proparly. what could probably go wraong

It is VERY rare to have to use more than one hidden layer. MATLAB's version of ELMAN uses a poorer approximation of timeseries network gradients. Using more layers just makes things worse. From the help documentation:

>> help elmannet

 elmannet Elman neural network.
   Elman networks are provided for historical interest. For much better
   results use narxnet, timedelaynet, or distdelaynet.
   Elman networks with two (or more) layers can learn any dynamic
   input-output relationship arbitrarily well given enough hidden
   neurons and enough input and layer delays. However, Elman networks
   use static derivative calculates instead of full dynamic calculates.

This results in a trade off of reduced training calculations, but the risk of poorer accuracy.

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

MATLAB: When I am the training a elman neural network it is working only with 5 or lower no. of hidden layers, as I tried to increase no of layers its giving only 50% accuracy which means network is not trained proparly. what could probably go wraong

Related Question