The methods of the INetwork interface are listed below. For a complete list of INetwork interface members, see the INetwork Members topic.
Public Instance Methods
 AddLayer | Overloaded. Add a layer to the neural network. The first layer added is the input layer, the last layer added is the output layer. This layer is added with a weighted synapse. |
| CalculateError | Calculate the error for this neural network. The error is calculated using root-mean-square(RMS). |
| CalculateNeuronCount | Calculate the total number of neurons in the network across all layers. |
| CheckInputSize | Check that the input size is acceptable, if it does not match the input layer, then throw an error. |
| CompareLayer | Used to compare one neural network to another, compare two layers. |
| Compute | Overloaded. Compute the output for a given input to the neural network. |
| Equals | Overloaded. Compare the two neural networks. For them to be equal they must be of the same structure, and have the same matrix values. |
| GetHashCode | Generate a hash code. |
| InferOutputLayer | Called to cause the network to attempt to infer which layer should be the output layer. |
| IsHidden | Determine if this layer is hidden. |
| IsInput | Determine if this layer is the input layer. |
| IsOutput | Determine if this layer is the output layer. |
| Reset | Reset the weight matrix and the thresholds. |
| ToString | Convert this object to a string. |
| Winner | Determine the winner for the specified input. This is the number of the winning neuron. |