Package | Description |
---|---|
org.joone.engine | |
org.joone.engine.learning | |
org.joone.io | |
org.joone.net | |
org.joone.structure | |
org.joone.util |
Modifier and Type | Class and Description |
---|---|
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.
|
Modifier and Type | Class and Description |
---|---|
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.
|
Modifier and Type | Class and Description |
---|---|
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.
|
Modifier and Type | Class and Description |
---|---|
class |
NestedNeuralLayer |
Modifier and Type | Class and Description |
---|---|
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.
|
Modifier and Type | Class and Description |
---|---|
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