| Name | Description |
|---|---|
| AnalyzeNetwork | |
| CalculateDepth | Utility class to calculate the depth that a layer is from the output layer. If there are multiple ways to get to the specified layer, then the longest depth is returned. This class is used by propagation training to ensure that the layers are always returned on a consistent order. |
| NetworkCODEC | This class will extract the "long term memory" of a neural network, that is the weights and bias values into an array. This array can be used to view the neural network as a linear array of doubles. These values can then be modified and copied back into the neural network. This is very useful for simulated annealing, as well as genetic algorithms. |
| NeuralStructure | |
| ValidateForFlat | Validate to determine if this network can be flattened. |