|
|
 |
 |
|
|
 |
|
|
|
|
|
|
|
|
|
|
NeuroSolutions for MATLAB Product Tour |
|---|
Step 3: Testing and Utilizing the Neural Network
After training, the performance of the neural network model can be evaluated on a new out-of-sample testing data set.-
>> [z_out, performance] = nsTest (mynet, z_in, z_desired);
>> performance
performance =
mse: 0.7316
nmse: 0.1728
correlation: 0.9095
percent_error: 13.1862
Production
Once you have created the network, trained and tested it to your satisfaction, the neural network is ready to be utilized in practice with production data.
-
>> p_out = nsProduction (mynet, p_in);
where p_in is the production input data and p_out is the network output for the production input data.
What is Production?
Let’s say you want a neural network to do voice recognition. To train the neural network you would record voice samples of people you know and use it as training data. The voice samples serve as the training input data and the text that they spoke serves as the training desired data. Once the neural network is trained it can be used in a real-world situation to perform voice recognition on voice samples of any individual. This process of using a neural network on data for which there is no desired output is called production.
Back | 
Tour Topics | Next
 |
 |