Outstar

Outstar network can associate a scalar input to a vector output for pattern recall. Learning algorithm is modified form of Hebbian learning rule.

 

In this configuration the from neuron activates a pattern of the to neurons

To create and train Outstar neural network with easyNeurons do the following:

  1. Choose Outstar architecture (in main menu choose Networks>Outstar)
  2. Enter architecture specific parameters (number of neurons in input layer)
  3. Create training set (in main menu choose Training >New Training Set)
  4. Train network
  5. Test network

Step 1. To create Outstar network, in main menu click Networks > Outstar

 Step 2. Enter number of neurons in input layer, and click Create button.

This will create the Outstar neural network with one neuron in input and eight in output layer.

Now we shall train this simple network, to learn from data. First we have to create the training set

Step 3.  In main menu click Training > New Training Set to open training set wizard.

Step 4. Train network

TODO

Step 5. Test network

TODO