org.neuroph.nnet
Class Perceptron
java.lang.Object
java.util.Observable
org.neuroph.core.NeuralNetwork
org.neuroph.nnet.Perceptron
- All Implemented Interfaces:
- java.io.Serializable, java.lang.Runnable
public class Perceptron
- extends NeuralNetwork
The Perceptron class that represents Perceptron neural network with some LMS
based learning algorithm.
- See Also:
neuroph.nnet.learning.LMS
,
neuroph.nnet.learning.StepDeltaRule
,
neuroph.nnet.learning.SigmoidDeltaRule
,
Serialized Form
Field Summary |
private static long |
serialVersionUID
The class fingerprint that is set to indicate serialization
compatibility with a previous version of the class. |
Constructor Summary |
Perceptron(int inputNeuronsNum,
int outputNeuronsNum)
Creates new Perceptron with specified number of neurons in input and
output layer, with Step trqansfer function |
Perceptron(int inputNeuronsNum,
int outputNeuronsNum,
TransferFunctionType transferFunctionType)
Creates new Perceptron with specified number of neurons in input and
output layer, and specified transfer function |
Method Summary |
private void |
createNetwork(int inputNeuronsNum,
int outputNeuronsNum,
TransferFunctionType transferFunctionType)
Creates perceptron architecture with specified number of neurons in input
and output layer, specified transfer function |
Methods inherited from class org.neuroph.core.NeuralNetwork |
addLayer, addLayer, addPlugin, calculate, createConnection, getInputNeurons, getLayerAt, getLayers, getLayersCount, getLayersIterator, getLearningRule, getNetworkType, getOutput, getOutputAsArray, getOutputNeurons, getPlugin, indexOf, learn, load, notifyChange, randomizeWeights, removeLayer, removeLayerAt, removePlugin, reset, run, save, setInput, setInput, setInputNeurons, setLearningRule, setNetworkType, setOutputNeurons, stopLearning, toString |
Methods inherited from class java.util.Observable |
addObserver, clearChanged, countObservers, deleteObserver, deleteObservers, hasChanged, notifyObservers, notifyObservers, setChanged |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait |
serialVersionUID
private static final long serialVersionUID
- The class fingerprint that is set to indicate serialization
compatibility with a previous version of the class.
- See Also:
- Constant Field Values
Perceptron
public Perceptron(int inputNeuronsNum,
int outputNeuronsNum)
- Creates new Perceptron with specified number of neurons in input and
output layer, with Step trqansfer function
- Parameters:
inputNeuronsNum
- number of neurons in input layeroutputNeuronsNum
- number of neurons in output layer
Perceptron
public Perceptron(int inputNeuronsNum,
int outputNeuronsNum,
TransferFunctionType transferFunctionType)
- Creates new Perceptron with specified number of neurons in input and
output layer, and specified transfer function
- Parameters:
inputNeuronsNum
- number of neurons in input layeroutputNeuronsNum
- number of neurons in output layertransferFunctionType
- neuron transfer function type
createNetwork
private void createNetwork(int inputNeuronsNum,
int outputNeuronsNum,
TransferFunctionType transferFunctionType)
- Creates perceptron architecture with specified number of neurons in input
and output layer, specified transfer function
- Parameters:
inputNeuronsNum
- number of neurons in input layeroutputNeuronsNum
- number of neurons in output layertransferFunctionType
- neuron transfer function type