NeuNet Pro Menu Items
Table Of Contents

Menu Items







Run Menu

Select a menu item

Configure This Project Split the data Go to SFAM/BackProp Training

Run... Configure this Project
  • This function must be used whenever a new project is created.
  • You will select a database and data table for the project.
  • You will select what field is to be predicted.
  • You will select which fields are to be used for making the prediction.
  • A project may be reconfigured at any time, but all previous training will be lost.

Run... Split the Data

  • This feature allows you to split your data into two groups - "Training Set" and "Testing Set".
  • The training set is used to train the neural network. The testing set is not seen during training.
  • Error reports on the Training screen are based on the training set. All other performance reports are based on the testing set.
  • Each set can be as large as 32,000 records. The training set must contain at least ten records. The testing set can be as small as one record.
  • You may overlap the split, so some rows appear in both sets. Indeed both sets may be identical.
  • Some of your rows can be omitted from both sets.
  • Remember larger data sets will be slower to train and test.

Run... Go To SFAM/BackProp Training

  • This function delivers you to the Training screen.
  • The actual neural network is developed during training.

A Complete Neural Network Development System

CorMac Technologies Inc.
34 North Cumberland Street ~ Thunder Bay ON P7A 4L3 ~ Canada
E m a i l