BAM

BAM (Bidirectional Associative Memory) is a type of hetero-associative memory, meaning given a pattern it can return another associated pattern of a different size. It is similar to the Hopfield network in that they are both forms of associative memory however, Hopfield nets return patterns of the same size. It is like Hopfield net with neurons separated into input and output layer without connections between the neurons in the same layer. [http://en.wikipedia.org/wiki/Bidirectional_Associative_Memory]

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

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

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

This will create the BAM neural network with nine neurons in input and two 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