UNSUPERVISED HEBBIAN NETWORK

Unsupervised Hebbian network is feedforward network that use unsupervised form of Hebbian learning rule. Hebb's principle states that weight between two neurons will increase if the two neurons activate simultaneously,and it is reduced if they activate separately. It can be summarized as "cells that fire together, wire together".[http://en.wikipedia.org/wiki/Hebbian_theory.htm]

Unsupervised Hebbian

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

  1. Choose Unsupervised Hebbian architecture (in main menu choose Networks> Unsupervised Hebbian)
  2. Enter architecture specific parameters (num of neurons)
  3. Create training set
  4. Set training parameters and start training
  5. Test network 

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

 

 Step 2. Enter number of neurons in input and output layer, choose Ramp transfer function as shown on picture below and click Create button.

 

 This will create the Unsupervised Hebbian neural network with two neurons in input, and one in output layer.

 

Step 4. Train network

TODO

Step 5. Test network

TODO