*********** Cosines.nns is a NeuNet Pro Sample File ***********

This file contains special properties that allow NeuNet Pro to recognize it
as authorized NeuNet sample data.  Anyone using the unlicensed version
of NeuNet Pro is welcome to experiment with this sample data.
Please do not modify this file, or it will lose its status as authorized sample data.

For further information about Neunet Pro and additional sample data,
please visit the NeuNet Pro website at http://www.cormactech.com/neunet

All of this data has been generated by CorMac Technologies Inc.

The provided NeuNet project attempts to train a neural network
to learn to predict the next point on a cosine wave by using
several previous points. 


    ***************  More about the Cosine Data *******************

                        C O S I N E    D A T A 
    (Train a neural net to predict next point along cosine wave)

 This project contains nine columns and 10,000 rows:
 [Index], [Y1], [Y2], [Y3],[Y4], [Y5], [Y6],[Y7], [Y8]
 The Y points are equally spaced along the previous 
 half wavelength of a cosine wave.  The rows are presented
 as a time series.

 NeuNet Pro was trained to predict [Y8] based on the
 previous seven Y values.

 NeuNet Pro default project settings were used.
 NeuNet Pro was trained on the first 5000 rows then tested on
 the remaining 5,000 rows. Accuracy was ~99.75% for both the
 training set and the test set.

 Attempts to predict [Y8] based solely on the [Index] value
 were unsuccessful.