All Packages from org.joone.dte.control.* to org.joone.dte.selection.*

Home >> All >> org >> joone >> [ dte Javadoc ]

•

• org.joone.dte: Javadoc index of package org.joone.dte.

Package Samples:

• org.joone.dte.selection
• org.joone.dte.factory
• org.joone.dte.control

Classes:

• TaskFactory: This interface must be implemented by any class that is capable to create tasks to elaborate (i.e. neural nets to train) starting from external parameters written in some formalism or language (e.g. XML) After the TaskFactory is created, the DTE calls on it the initialize() method, and then, for each neural network it needs to elaborate, the getNextTask() is called, until it returns null. The developer has two possibilities, based on the creation mechanism he wants to implement: 1 - In order to avoid to occupy many memory, the initialize method doesn't create neural networks, as they are created ...
• RmseCondition: This condition verifies if the actual population has reached the maxRmse specified as parameter. if validation = true, the validation rmse is checked, otherwise the control is done on the training rmse (the default). if mean = true, the condition is verified only if the average rmse of the population is below maxRmse, otherwise the control is done on the fittest neural network. As this class extends the MaxCyclesCondition, also a max number of iterations can be specified, in order to stop the DTE if the maxRmse is not reached after that number of cycles.
• MultiplierFactory: This class gets in input a TaskList and generates N copies of each element of the list. Moreover, if noise > 0.0, for each generated element: If randomize = false: applyes a noise to the weights If randomize = true: initialize the weights
• StopCondition: This interface represents the verifier of the stop condition. Its method done is called after the processing phase to verify if the DTE must continue to eleborate the next cycle.
• SimpleFactory: Very simple implementation of the TaskFactory interface. It is not many useful, but can be used as starting point to build more complex TaskFactory implementations.
• ChainedFactory: This TaskFactory calls in sequence all the TaskFactory objects contained in the Chain parameter, and returns the sum of the generated tasks.
• AlwaysStop: Stops the DTE without conditions. Indeed this class is absolutely useles, because if no condition has been defined, the DTE stops anyway.
• Selector: This interface represents the post-processing plugins. The job calls its execute method to prepare the next list of tasks to elaborate.
• FittestSelector: This selector selects the fittest 'num' neural networks, i.e. those having the lowest training or validation RMSE.
• TaskListFactory: Factory that genetares the tasks starting from the content of a TaskList object
• TaskList: This class is a container of Tasks described by instances of TaskDescriptor
• TaskDescriptor: This class is used to describe a task entry in the task list XML file
• MaxCyclesCondition: This StopCondition class stops after maxCycles cycles
• NetTaskEntry
• JooneJobRunner
• JooneJob

Home | Contact Us | Privacy Policy | Terms of Service