|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.encog.neural.networks.structure.NetworkCODEC
public final class 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.
Method Summary | |
---|---|
static void |
arrayToNetwork(double[] array,
MLMethod network)
Use an array to populate the memory of the neural network. |
static boolean |
equals(BasicNetwork network1,
BasicNetwork network2)
Determine if the two neural networks are equal. |
static boolean |
equals(BasicNetwork network1,
BasicNetwork network2,
int precision)
Determine if the two neural networks are equal. |
static int |
networkSize(MLMethod network)
Determine the network size. |
static double[] |
networkToArray(MLMethod network)
Convert to an array. |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Method Detail |
---|
public static void arrayToNetwork(double[] array, MLMethod network)
array
- An array of doubles.network
- The network to encode.public static boolean equals(BasicNetwork network1, BasicNetwork network2)
network1
- The first network.network2
- The second network.
public static boolean equals(BasicNetwork network1, BasicNetwork network2, int precision)
network1
- The first network.network2
- The second network.precision
- How many decimal places to check.
public static int networkSize(MLMethod network)
network
- The network.
public static double[] networkToArray(MLMethod network)
network
- The network to encode.
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |