메소드 | 설명 | |
---|---|---|
AddPattern ( IMLData pattern ) : void |
Train the neural network for the specified pattern. The neural network can be trained for more than one pattern. To do this simply call the train method more than once.
|
|
Compute ( IMLData input ) : IMLData |
Note: for Hopfield networks, you will usually want to call the "run" method to compute the output. This method can be used to copy the input data to the current state. A single iteration is then run, and the new current state is returned.
|
|
HopfieldNetwork ( ) : System |
Default constructor.
|
|
HopfieldNetwork ( int neuronCount ) : System |
Construct a Hopfield with the specified neuron count.
|
|
Run ( ) : void |
Perform one Hopfield iteration.
|
|
RunUntilStable ( int max ) : int |
Run the network until it becomes stable and does not change from more runs.
|
|
UpdateProperties ( ) : void |
|
메소드 | 설명 | |
---|---|---|
ConvertHopfieldMatrix ( Matrix delta ) : void |
Update the Hopfield weights after training.
|
public AddPattern ( IMLData pattern ) : void | ||
pattern | IMLData | The pattern to train for. |
리턴 | void |
public final Compute ( IMLData input ) : IMLData | ||
input | IMLData | The input pattern. |
리턴 | IMLData |
public HopfieldNetwork ( int neuronCount ) : System | ||
neuronCount | int | The neuron count. |
리턴 | System |
public RunUntilStable ( int max ) : int | ||
max | int | The maximum number of cycles to run before giving up. |
리턴 | int |