Instar

Instar network is able to recognize a single vector pattern based on a modified Hebbian rule. The network has single McCulloch-Pitts neuron in output layer.

 

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

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

  1. Choose Instar architecture (in main menu choose Networks>Instar)
  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 Instar network, in main menu click Networks > Instar

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

This will create the Instar neural network with eight neurons in input and one 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