Uses of Interface
org.joone.inspection.Inspectable

Packages that use Inspectable
org.joone.engine   
org.joone.engine.learning   
org.joone.io   
org.joone.net   
org.joone.structure   
org.joone.util   
 

Uses of Inspectable in org.joone.engine
 

Classes in org.joone.engine that implement Inspectable
 class BiasedLinearLayer
          This layer consists of linear neurons, i.e.
 class BufferedSynapse
          This class implements a synapse that permits to have asynchronous methods to write output patterns.
 class ContextLayer
          The context layer is similar to the linear layer except that it has an auto-recurrent connection between its output and input.
 class DelayLayer
          Delay unit to create temporal windows from time series
O---> Yk(t-N)
|
...
 class DelaySynapse
          This Synapse connects the N input neurons with the M output neurons using a matrix of FIRFilter elements of size NxM.
 class DirectSynapse
          This is forward-only synapse.
 class FreudRuleFullSynapse
          Deprecated. possible bug in implementation
 class FullSynapse
           
 class GaussianLayer
          This layer implements the Gaussian Neighborhood SOM strategy.
 class GaussLayer
          The output of a Gauss(ian) layer neuron is the sum of the weighted input values, applied to a gaussian curve (exp(- x * x)).
 class KohonenSynapse
          This is an unsupervised Kohonen Synapse which is a Self Organising Map.
 class Layer
          The Layer object is the basic element forming the neural net.
 class LinearLayer
          The output of a linear layer neuron is the sum of the weighted input values, scaled by the beta parameter.
 class LogarithmicLayer
          This layer implements a logarithmic transfer function.
 class MemoryLayer
           
 class RbfGaussianLayer
          This class implements the nonlinear layer in Radial Basis Function (RBF) networks using Gaussian functions.
 class RbfInputSynapse
          The synapse to the input of a radial basis function layer should't provide a single value to every neuron in the output (RBF) layer, as is usual the case.
 class RbfLayer
          This is the basis (helper) for radial basis function layers.
 class SangerSynapse
          This is the synapse useful to extract the principal components from an input data set.
 class SigmoidLayer
          The output of a sigmoid layer neuron is the sum of the weighted input values, applied to a sigmoid function.
 class SimpleLayer
          This abstract class represents layers that are composed by neurons that implement some transfer function.
 class SineLayer
          The output of a sine layer neuron is the sum of the weighted input values, applied to a sine (sin(x)).
 class SoftmaxLayer
          The outputs of the Softmax layer must be interpreted as probabilities.
 class Synapse
          The Synapse is the connection element between two Layer objects.
 class TanhLayer
          Layer that applies the tangent hyperbolic transfer function to its input patterns
 class WTALayer
          This layer implements the Winner Takes All SOM strategy.
 

Uses of Inspectable in org.joone.engine.learning
 

Classes in org.joone.engine.learning that implement Inspectable
 class AbstractTeacherSynapse
          This class provides a framework to extend in order to implement various teachers, just by overriding or implementing certain functions different functionality can easily implemented.
 class ComparisonSynapse
          Final element of a neural network; it permits to compare the outcome of the neural net and the input patterns from a StreamInputSynapse connected to the 'desired' property.
 class FahlmanTeacherSynapse
           This class extends the normal Teacher synapse and implements the Fahlman 40-20-40 criterion (the values can be changed).
 class TeacherSynapse
          Final element of a neural network; it permits to calculate both the error of the last training cycle and the vector containing the error pattern to apply to the net to calculate the backprop algorithm.
 

Uses of Inspectable in org.joone.io
 

Classes in org.joone.io that implement Inspectable
 class FileInputSynapse
          Allows data to be presented to the network from a file.
 class FileOutputSynapse
           
 class ImageInputSynapse
          This synapse collects data from Image files or Image objects and feeds the data from the Images into the Neural network.
 class ImageOutputSynapse
          This class collects the output from the connected layer and places it into an image file.
 class InputConnector
           
 class InputSwitchSynapse
          This class acts as a switch that can connect its output to one of its connected input synapses.
 class JDBCInputSynapse
          The JDBCInputSynapse provides support for data extraction from a database.
 class JDBCOutputSynapse
          The JDBCOutputSynapse provides support for data input to a database.
 class MemoryInputSynapse
           
 class MemoryOutputSynapse
           
 class MultipleInputSynapse
          This class reads sequentially all the connected input synapses, in order to be able to use multiple sources as inputs.
 class StreamInputSynapse
           
 class StreamOutputSynapse
           
 class URLInputSynapse
          Allows data extraction from the internet or a file specified by a Universal Resource Locator or URL.
 class XLSInputSynapse
          This class allows data to be presented to the network from an Excel XLS formatted file.
 class XLSOutputSynapse
          This class allows data to be read from an Excel XLS formatted file.
 class YahooFinanceInputSynapse
          The YahooFinanceInputSynapse provides support for financial data input from financial markets.
 

Uses of Inspectable in org.joone.net
 

Classes in org.joone.net that implement Inspectable
 class NestedNeuralLayer
           
 

Uses of Inspectable in org.joone.structure
 

Classes in org.joone.structure that implement Inspectable
 class NetworkLayer
          Wraps an existing joone network into a single layer.
(package private)  class PatternForwardedSynapse
          This class/synapse is only used to inform a Nakayama object whenever a single patterns has been forwarded through the network.
 

Uses of Inspectable in org.joone.util
 

Classes in org.joone.util that implement Inspectable
 class LearningSwitch
          This class is useful to switch the input data set of a neural network from a training set to a validation set depending on the 'validation' parameter contained in the Monitor object.
 



Submit Feedback to pmarrone@users.sourceforge.net