Package org.encog.ml.train.strategy
-
Interface Summary Interface Description Strategy Training strategies can be added to training algorithms. -
Class Summary Class Description Greedy A simple greedy strategy.HybridStrategy A hybrid stragey allows a secondary training algorithm to be used.RequiredImprovementStrategy The reset strategy will reset the weights if the neural network fails to improve by the specified amount over a number of cycles.ResetStrategy The reset strategy will reset the weights if the neural network fails to fall below a specified error by a specified number of cycles.StopTrainingStrategy This strategy will indicate once training is no longer improving the neural network by a specified amount, over a specified number of cycles.
DMelt 3.0 © DataMelt by jWork.ORG