|
Heuristic Neural Training dialog box |
|
Use this dialog box to quickly train neural networks.
Limits
Specifies the error type that appears in the Statistics section and the error type that the Target Error value is compared with. Select one of:
| · | Mean Square: |
| · | Mean Absolute: |
| · | Mean Distance: |
Where 
is the ith target value, 
the ith output value, and N the number of target values.
Specifies the error value at which network training stops. Type in this box the error to which you want to approximate the underlying function, or leave the error as zero to let network training approximate the function as much as possible.
Options
Indicates the maximum number of times that this algorithm tries to minimize the approximation error if previous tries are unsuccessful. Type the maximum number of times you want to allow this algorithm to try approximating the underlying function.
 | An underlying function is considered approximated when the Target Error value is reached. |
The maximum number of tries is limited to 32,767.
Specifies the maximum number of epochs that make up a try. Type in this box the maximum number of epochs you want to allow for each try.
| The maximum number of epochs is limited to 32,767. |
Check this option to shock the network weights after every unsuccessful try.
| This option is not available when Maximum Tries is set to one. |
Refer to Shock Factor (Network Weights Shock dialog box) for information on the amount by which network weights will change when shocked.
Statistics
Displays the total number of epochs that have been used to train this network so far.
Displays the total number of tries and epochs that have elapsed since the last safepoint as
<NumberOfTries> : <NumberOfEpochs>
Displays the training error corresponding to the last safepoint in the format specified by Target Error Type.
Displays the training error corresponding to the most recent try epoch in the format specified by Target Error Type.
Displays the test error corresponding to the last safepoint in the format specified by Target Error Type.
Refer to the Data Usage tab (Training Options dialog box) for additional information on test areas.
Displays the test error corresponding to the most recent try epoch in the format specified by Target Error Type.
Training Errors
Plots epoch training errors in the format specified by Target Error Type when the associated Plot box is checked.
| This mini-plot box will only retain the last 4,096 points. |
Refer to Mini-Plot box shortcut commands for additional information on the use of mini-plot boxes.
Check this box to plot epoch training errors.
| Plotting epoch training errors reduces the speed of this algorithm. If your training area is large, you should consider turning this option on for limited periods of time only. |
Click this button to remove all the epoch training error points from the associated mini-plot box.
Plots safepoint training errors in the format specified by Target Error Type when the associated Plot box is checked.
| This mini-plot box will only retain the last 4,096 points. |
Refer to Mini-Plot box shortcut commands for additional information on the use of mini-plot boxes.
Check this box to plot safepoint training errors.
Click this button to remove all safepoint training error points from the corresponding mini-plot box.
Test Errors
Plots epoch test errors in the format specified by Target Error Type when the associated Plot box is checked.
| This mini-plot box will only retain the last 4,096 points. |
Refer to Mini-Plot box shortcut commands for additional information on the use of mini-plot boxes.
Check this box to plot epoch test errors.
| Plotting epoch test errors reduces the speed of this algorithm. If your test area is large, you should consider selecting this option for limited periods of time. |
Click this button to remove all the epoch test error points from the associated mini-plot box.
Plots safepoint test errors in the format specified by Target Error Type when the associated Plot box is checked.
| This mini-plot box will only retain the last 4,096 points. |
Refer to Mini-Plot box shortcut commands for additional information on the use of mini-plot boxes.
Check this box to plot safepoint test errors.
Click this button to remove all the safepoint test error points from the associated mini-plot box.
Specifies the color with which the series corresponding to the epoch error values are plotted. Click this box to change the current color.
Specifies the color with which the series corresponding to the safepoint error values are plotted. Click this box to change the current color.
Displays the Training Options dialog box so you can change settings during training.
Displays the Network Weights Shock dialog box to alter the network connection weights and to specify the amount by which to carry this change.
| The weight modification factor, Shock Factor, specified in the Network Weights Shock dialog box will remain in effect for the duration of the current training session only. This is the same factor used for shocking the network weights when you select the Auto Shock option. |
Refer to the Network Weights Shock dialog box for additional information on this topic.
Click this button to reset the training state of this neural network. This action sets the network weights to random values, according to the settings previously indicated on the Weights Initialization tab (Network Definition dialog box).
| It is not an uncommon practice to reset a neural network several times before reaching a satisfactory training level. You can reset the state of the current network independently of its previous state. To affect a previous state you are required to Apply the changes of this session throughout the different dialog box layers. |
 | If you are planning to reset a neural network for retraining, consider you can copy the network in order to carry new training on the duplicate. |
Click this button to reload the last saved training state of this neural network.
| This command destroys this session's training state. |
Click this button to start, stop, and continue training.
Applies the current safepoint state to the neural network.
| The current safepoint state is not necessarily the same as the current running state. |
Prompts you to save changes and closes the dialog box. Click this button when you have finished network training.
| You can continue training at a later time, at the same safepoint where you left. |
Click this button to display Help on some element of this dialog box. The mouse pointer changes to an arrow and question mark. Then click somewhere in the dialog box, such as on a button or edit box. The Help topic will be shown for the item you clicked.
Sponsored
Try Predictive Systems Lab
Need Help?
Contact support