< Previous page

Freezes

Freezes

The Freezes dialog is used to set the node freeze levels and the way they are decremented while the network is learning.

 

After the initial number of training cycles are run the freeze levels are applied in the reverse order of the node importance. All nodes are considered, not just the inputs. The least important node has the lowest freeze level. The most important node has the highest freeze levels. Any nodes with their freeze level above zero is excluded from the learning process and their activation does not change.   Frozen input nodes have their activation set to the median value of the input range.   The freeze levels are reduced as learning progresses so that the nodes are progressively added to the learning process.     When learning has finished the input importance and sensitivity measures are more accurate.

1 . RemoveRemove

Remove

Check to remove the freezes that are still set from previous runs.

2 . Types to freezeTypes to freeze

Types to freeze

Check the node types to freeze.

3 . Set freezesSet freezes

Set freezes

Check to allow freezes to be applied.

4 . Initial cyclesInitial cycles

Initial cycles

Enter the number of training cycles before freezes are applied.

5 . First node levelFirst node level

First node level

Enter the freeze level to apply to the first node.

6 . IncreaseIncrease

Increase

Enter the freeze level to increase for each node.

7 . ReduceReduce

Reduce

Check Reduce to allow the freezes to be decremented while the network is learning.

8 . Reduce levelsReduce levels

Reduce levels

Enter the freeze level reduction.

9 . Reduce cyclesReduce cycles

Reduce cycles

Enter the training cycles to run between every freeze level decrement.

10 . OK buttonOK button

OK button

Press OK to accept all the settings and close the dialog.

11 . Cancel buttonCancel button

Cancel button

Press Cancel to reject all the settings and close the dialog.

< Previous page