|
From Data to Neural Network to Results.
Creating and training a neural network from your data is a simple five step process. Using the neural network to produce results is just as easy.
|
|
Five steps to create and train a neural network from a data file.
When learning stops the neural network can be used.
Copyright
©
2002-2008 Neural Planner Software Ltd |
File > New to create a blank grid. The grid is
initialized.
File > Import to import the data into the grid. The
import dialogs are already partially filled in. Just a few
clicks and the data appears in the grid.
Action > New Network
to create a neural network from the grid. The neural
network dialog is already set to produce the input layer, one
hidden layer and the output layer. One click and a fully
connected neural network is created.
Action > Change
Controls to set up the training and validating controls.
The controls dialog is initialized with the default settings.
Any training and validating controls can be adjusted or just
press enter to use the defaults.
Action > Start
Learning to train and validate the neural network.
Learning will run until a stop is reached. 
Query > Query to
interrogate the neural network interactively.
Query > File Query
to interrogate the neural network and create a results file.