public class TrainingDispatcher
extends java.lang.Thread
| Constructor and Description |
|---|
TrainingDispatcher(NeuralNet p_net,
Symbol[] p_symbols,
int p_loops,
int p_cycles,
TrainPanel p_parent,
double p_MSEMin,
int p_offset,
double p_entropy,
OCRManager p_OCR)
Creates a new training dispatcher with the parmeters given.
|
| Modifier and Type | Method and Description |
|---|---|
void |
run()
Runs the training analysis
|
activeCount, checkAccess, clone, countStackFrames, currentThread, destroy, dumpStack, enumerate, getAllStackTraces, getContextClassLoader, getDefaultUncaughtExceptionHandler, getId, getName, getPriority, getStackTrace, getState, getThreadGroup, getUncaughtExceptionHandler, holdsLock, interrupt, interrupted, isAlive, isDaemon, isInterrupted, join, join, join, resume, setContextClassLoader, setDaemon, setDefaultUncaughtExceptionHandler, setName, setPriority, setUncaughtExceptionHandler, sleep, sleep, start, stop, stop, suspend, toString, yieldpublic TrainingDispatcher(NeuralNet p_net, Symbol[] p_symbols, int p_loops, int p_cycles, TrainPanel p_parent, double p_MSEMin, int p_offset, double p_entropy, OCRManager p_OCR)
p_net - The neural net to trainp_symbols - The symbols to train the given net wirhp_loops - The number of times to loop all training data withp_cycles - The number of cycles per character to trainp_parent - The listener to alert to eventsp_MSEMin - The target MSE to hit during trainingp_offset - The offset until the beginning of the net's outputs in the output stackp_entropy - The amount of entropy, 0 to 1, to train with