next up previous contents index
Next: ART1_Weights Up: Using the Graphical Previous: Topological_Order

Initialization Functions

   

In order to work with various neural network models and learning algorithms, different initialization functions that initialize the components of a net are required. Backpropagation, for example, will not work properly if all weights are initialized to the same value.

To select an initialization function, one must click in the INIT line of the control panel.

The following initialization functions are available:

All these functions receive their input from the five init parameter fields in the control panel. See figure gif

Here is a short description of the different initialization functions:





Niels.Mache@informatik.uni-stuttgart.de
Tue Nov 28 10:30:44 MET 1995