Navigation
API > API/Plugins > API/Plugins/LearningAgents
Normalization options for neural network inputs & outputs.
| Name | ELearningAgentsNormalization |
| Type | enum |
| Header File | /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgents/Public/LearningAgentsNeuralNetwork.h |
| Include Path | #include "LearningAgentsNeuralNetwork.h" |
Syntax
enum ELearningAgentsNormalization
{
Manual = 0,
AutoShared = 1,
AutoPerDimension = 2,
}
Values
| Name | Remarks |
|---|---|
| Manual | Uses user specified scales and biases to normalize/denormalize network dataflow at the cpp schema layer. |
| AutoShared | Uses dataset derived standard deviation and mean as scales and biases to normalize/denormalize network dataflow. |
| AutoPerDimension | Uses dataset derived standard deviation and mean as scales and biases to normalize/denormalize network dataflow. |