Workspace Node: SANN Regression/Classification/Time Series/Clustering - Specifications - Initialization Tab
In the SANN Regression, SANN Classification, SANN Time Series (Regression), SANN Time Series (Classification), or SANN Clustering node dialog box, under the Specifications heading, select the Initialization tab to access the following options.
| Element Name | Description |
|---|---|
| Seed control for network initialization | Use the options in this box to specify a seed that will be used to randomly generate the initial network weights. You have the choice of either specifying the seed value or letting SANN use the system time to provide the algorithm with a seed. In the latter case, no two analyses will be the same (which is the recommended option). |
| Use fixed seed | Select this check box to use the specified seed which will be used in the random generation of network weights. |
| Seed value | Specify the seed that will be used to randomly generate the initial values of the network weights.
Options / C / W. See Common Options. |
| OK | Click the OK button to accept all the specifications made in the dialog box and to close it. The analysis results will be placed in the Reporting Documents node after running (updating) the project. |
Copyright © 2021. Cloud Software Group, Inc. All Rights Reserved.