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

Remove

1. Remove
Check to remove the freezes that are still set from previous runs.
2

Types to freeze

2. Types to freeze
Check the node types to freeze.
3

Set freezes

3. Set freezes
Check to allow freezes to be applied.
4

Initial cycles

4. Initial cycles
Enter the number of training cycles before freezes are applied.
5

First node level

5. First node level
Enter the freeze level to apply to the first node.
6

Increase

6. Increase
Enter the freeze level to increase for each node.
7

Reduce

7. Reduce
Check Reduce to allow the freezes to be decremented while the network is learning.
8

Reduce levels

8. Reduce levels
Enter the freeze level reduction.
9

Reduce cycles

9. Reduce cycles
Enter the training cycles to run between every freeze level decrement.
10

OK button

10. OK button
Press OK to accept all the settings and close the dialog.
11

Cancel button

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

Created with help of DrExplain