Maxnet is an implementation of a maximum-finding function. With each iteration, the neurons’ activations will decrease until only one neuron remains active. The “winner” is neuron that had the greatest output.

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

  1. Create Neuroph project
  2. Create Maxnet network
  3. Test network 

Step 1. To create Neuroph project click File > New Project.


Select Neuroph Project, click Next.


Enter project name and location, click Finish.

This created the project, next create neural network.

Step 2. To create Maxnet network, click File > New File


Select project from Project drop-down menu, select Neural Network file type, click next.


Enter network name, select Maxnet network type, click next.


  Enter number of Createbutton.


This will create the Maxnet neural network with four neurons in input and four in output layer. By default, neurons in input layer will have Linear, and in output Ramp transfer functions.

For this type of neural network there is no training process.


 Step 3. Now use Set Input button to see how this network works.


This opens Set Network Input dialog in which you can enter input values for network separated with white space.


The result of network test is shown on picture below. Only the third output neuron is fireing, because the corresponding input neuron has maximum input value.