Index

A B C D E F G H I L M N O P R S T U W
All Classes and Interfaces|All Packages

A

addLeftConnections(Connection) - Method in class ann4j.Neuron

This function adds a connection to the leftConnections list.

addNeuron(Neuron) - Method in class ann4j.Layer

This function adds a neuron to the list of neurons

addNeuronToBeObserved(int, int) - Method in class ann4j.NeuronObserver

Add a neuron to the list of objects to be observed.

addObjectToBeObserved(Observable) - Method in class ann4j.NeuronObserver

This function adds an object to the list of objects that this object will observe.

addObjectToBeObserved(Observable) - Method in interface ann4j.Observer

Add an object to the list of objects to be observed.

addRightConnections(Connection) - Method in class ann4j.Neuron

This function adds a connection to the rightConnections list

ann4j - package ann4j

average(double[]) - Static method in class ann4j.NN

It takes an array of doubles, adds them all together, divides by the length of the array, and returns the result

average(ArrayList<Double>) - Static method in class ann4j.NN

It takes an ArrayList of Doubles as input, and returns the average of the elements in the ArrayList

B

backPropagate() - Method in class ann4j.Connection

The backpropagation algorithm is calculating the gradient of the loss function with respect to the weight.

backwardPropagate() - Method in class ann4j.Layer

This function iterates through the list of neurons and calls the backwardPropagate method on each neuron

backwardPropagate() - Method in class ann4j.LayerManager

For each layer in the network, starting from the last layer, call the backwardPropagate function of that layer

backwardPropagate() - Method in class ann4j.Neuron

The neuron first sets its delta, then backpropagates through all of its left connections, and then changes its bias

bias - Variable in class ann4j.Neuron

C

calculateActivationForwardPropagation() - Method in class ann4j.Connection

Calculate the activation of the left neuron times the weight of the connection.

calculateMSE() - Method in class ann4j.LayerManager

This function calculates the mean squared error of the network

calculateMSE(OutputLayer, ArrayList<Double>) - Static method in class ann4j.MeanSquaredErrorCalculator

The function takes in an output layer and an array list of expected outputs.

changeWishlist - Variable in class ann4j.Connection

clear() - Method in class ann4j.NeuronObserver

Clearing the list of objects that this object will observe.

clear() - Method in interface ann4j.Observer

confusionMatrix - Variable in class ann4j.ModelEvaluator

Connection - Class in ann4j

Connection(Neuron, Neuron) - Constructor for class ann4j.Connection

D

delta - Variable in class ann4j.Neuron

deregisterObserver(NeuronObserver) - Method in class ann4j.Neuron

deregisterObserver(NeuronObserver) - Method in interface ann4j.Observable

Deregisters the observer from the observable

display() - Static method in class ann4j.parameter

Ends the display of the current page.

E

end() - Static method in class ann4j.Writer

This function closes the file that we opened in the start() function

exclude() - Method in class ann4j.Neuron

This function sets the value of the isIncluded variable to false, after which it wont be included in forward propagation

expectedLayer - Variable in class ann4j.Trainer

expectedOutputArray - Variable in class ann4j.MNISTDataBaseFileReader

ExpectedOutputArrayList - Static variable in class ann4j.LayerManager

F

filename - Variable in class ann4j.InputFileReader

fileName - Variable in class ann4j.MNISTDataBaseFileReader

forwardPropagate() - Method in class ann4j.Layer

The forwardPropagate function iterates through the list of neurons and calls the forwardPropagate method on each neuron

forwardPropagate() - Method in class ann4j.LayerManager

The forwardPropagate() method is called on every layer in the listOfLayers ArrayList, except the input layer

forwardPropagate() - Method in class ann4j.Neuron

The activation of the neuron is set to the rectified value of the weighted sum of the left connections plus the bias

forwardPropagatewithExclusionInputLayer() - Method in class ann4j.LayerManager

The function calculates the relevance of each pixel in the input image by excluding each pixel and calculating the loss function

forwardPropagatewithExclusionInputLayerOnKSamples(int) - Method in class ann4j.Trainer

G

generateExpectedOutputArrayFromLabel() - Method in class ann4j.MNISTDataBaseFileReader

This function is responsible for generating the output neurons

generateInputFromBigArray(ArrayList<Double>) - Method in class ann4j.MNISTDataBaseFileReader

It takes the array of all the values in the dataset and returns an array of all the values except the first one

getAccuracy() - Method in class ann4j.ModelEvaluator

It returns the accuracy of the player as a percentage

getActivation() - Method in class ann4j.Neuron

This function returns the activation of the neuron

getBackwardWeightedSum() - Method in class ann4j.Connection

The function returns the gradient of the loss function with respect to the weight

getBatchsize() - Static method in class ann4j.parameter

getBias() - Method in class ann4j.Neuron

This function returns the bias of the neuron

getBiasLearningRate() - Static method in class ann4j.parameter

This function returns the bias learning rate

getconfidence() - Method in class ann4j.LayerManager

It returns the confidence of the most significant neuron in the output layer

getDelta() - Method in class ann4j.Neuron

This function returns the value of the delta variable

getEpsillion() - Static method in class ann4j.parameter

Get the value of epsillion for relevance propagation

getExpectedOutputArray() - Method in class ann4j.InputFileReader

This function returns an ArrayList of Doubles that represents the expected output of the neural network

getExpectedOutputArray() - Method in class ann4j.MNISTDataBaseFileReader

This function returns the expected output array

getInputArray() - Method in class ann4j.InputFileReader

This function returns an ArrayList of Doubles that represents the input layer of the neural network

getInputArray() - Method in class ann4j.MNISTDataBaseFileReader

This function returns the inputArray

getInputLayer() - Method in class ann4j.LayerManager

This function returns the input layer of the neural network.

getInstance() - Static method in class ann4j.HiddenLayerNeuronBehaviour

The function returns an instance of the class if one exists, otherwise it creates a new instance and returns it

getInstance() - Static method in class ann4j.InputLayerNeuronBehaviour

(singleton pattern) If the instance of the class is null, create a new instance of the class and return it

getInstance() - Static method in class ann4j.OutputLayerNeuronBehaviour

If myInstance is null, create a new instance of OutputLayerNeuronBehaviour and assign it to myInstance.

getLabel() - Method in class ann4j.InputFileReader

This function returns the label.

getLabel() - Method in class ann4j.MNISTDataBaseFileReader

This function is responsible for setting the labels of the data.

getLayer(int) - Method in class ann4j.LayerManager

This function returns the layer at the specified index

getLayerArray() - Static method in class ann4j.parameter

getLayerManager() - Method in class ann4j.Trainer

Returns the LayerManager object that is used to manage the layers in this map.

getLayerNum() - Method in class ann4j.Neuron

This function returns the layer number of the neuron

getLearningRate() - Static method in class ann4j.parameter

getListOfNeurons() - Method in class ann4j.Layer

This function returns the list of neurons in the layer

getModelEvaluator() - Static method in class ann4j.parameter

> The function `getModelEvaluator()` returns a new instance of the class `ModelEvaluator`

getModelEvaluator() - Method in class ann4j.Trainer

This function returns the model evaluator

getMostSignificantNeuronAsPredictionInHiddenLayer() - Method in class ann4j.LayerManager

It returns the index of the most significant neuron in the hidden layer

getMostSignificantNeuronNumAsPrediction() - Method in class ann4j.LayerManager

It returns the index of the neuron in the output layer that has the highest activation value

getNeuron(int) - Method in class ann4j.Layer

This function returns the neuron at the specified index in the list of neurons

getNeuronNum() - Method in class ann4j.Neuron

This function returns the number of neurons in the layer

getNeuronNumberToBeTestedinRelavancePropagation() - Static method in class ann4j.LayerManager

This function returns the number of neurons to be tested in relevance propagation

getOutput() - Method in class ann4j.LayerManager

Return the last layer in the listOfLayers ArrayList.

getOutputLayer() - Method in class ann4j.LayerManager

This function returns the output layer of the neural network

getPredictionFromNeuronNum(int) - Method in class ann4j.InputFileReader

> This function takes in the most significant neuron number and returns the prediction

getPredictionFromNeuronNum(int) - Method in class ann4j.MNISTDataBaseFileReader

getRandom() - Static method in class ann4j.NN

This function returns a random number between 0 and 1.

getSize() - Method in class ann4j.Layer

This function returns the number of neurons in the layer

getSmallSignedRandom() - Static method in class ann4j.NN

It returns a random number between -0.5 and 0.5

getTestingAccuracy() - Method in class ann4j.ModelEvaluator

This function returns the testing accuracy of the model

getTestingFileReader() - Static method in class ann4j.parameter

This function returns the testingFileReader object

getTrainingAccuracy() - Method in class ann4j.ModelEvaluator

This function returns the training accuracy of the model

getTrainingFileReader() - Static method in class ann4j.parameter

This function returns the trainingFileReader object

getWeight() - Method in class ann4j.Connection

This function returns the weight of the object

getWeightedSum() - Method in class ann4j.Neuron

It calculates the weighted sum of the left connections of the neuron

H

HiddenLayer - Class in ann4j

HiddenLayer(int) - Constructor for class ann4j.HiddenLayer

HiddenLayerNeuronBehaviour - Class in ann4j

I

include() - Method in class ann4j.Neuron

This function sets the isIncluded variable to true after which it will be included in forward propagation

initializeList(int) - Method in class ann4j.ModelEvaluator

Initialize the confusion matrix to all zeros

initializeWeights() - Method in class ann4j.Connection

This function initializes the weight of the connection to a small random number

inputArray - Variable in class ann4j.MNISTDataBaseFileReader

InputFileReader - Class in ann4j

InputFileReader(String) - Constructor for class ann4j.InputFileReader

inputLayer - Variable in class ann4j.LayerManager

inputLayer - Variable in class ann4j.Trainer

InputLayer - Class in ann4j

InputLayer(int) - Constructor for class ann4j.InputLayer

InputLayerNeuronBehaviour - Class in ann4j

L

label - Variable in class ann4j.MNISTDataBaseFileReader

label - Variable in class ann4j.Trainer

Layer - Class in ann4j

Layer(int) - Constructor for class ann4j.Layer

LayerManager - Class in ann4j

LayerManager(int[]) - Constructor for class ann4j.LayerManager

layerNum - Variable in class ann4j.Layer

layerNum - Variable in class ann4j.Neuron

leakyrelu(double) - Static method in class ann4j.NN

If the number is greater than 0, return the number, else return 0.1 times the number

leftConnections - Variable in class ann4j.Neuron

leftNeuron - Variable in class ann4j.Connection

listOfLayers - Variable in class ann4j.LayerManager

listOfNeurons - Variable in class ann4j.Layer

lossFunction - Static variable in class ann4j.LayerManager

M

main(String[]) - Static method in class Main

Main - Class in Unnamed Package

Main() - Constructor for class Main

MeanSquaredErrorCalculator - Class in ann4j

MeanSquaredErrorCalculator() - Constructor for class ann4j.MeanSquaredErrorCalculator

MNISTDataBaseFileReader - Class in ann4j

MNISTDataBaseFileReader(String, int) - Constructor for class ann4j.MNISTDataBaseFileReader

ModelEvaluator - Class in ann4j

ModelEvaluator() - Constructor for class ann4j.ModelEvaluator

myBehaviour - Variable in class ann4j.Layer

myBehaviour - Variable in class ann4j.Neuron

myLayerManager - Variable in class ann4j.Trainer

myWriter - Static variable in class ann4j.Writer

N

Neuron - Class in ann4j

Neuron() - Constructor for class ann4j.Neuron

NeuronBehaviour - Interface in ann4j

neuronNum - Variable in class ann4j.Neuron

NeuronObserver - Class in ann4j

NeuronObserver() - Constructor for class ann4j.NeuronObserver

next() - Method in class ann4j.InputFileReader

This function goes to next line of the inputfile and is responsible for setting all input parameters

next() - Method in class ann4j.MNISTDataBaseFileReader

It reads the next line of the file, converts it into a two double arrays, and then sets the label and expected output array

NN - Class in ann4j

notifyObservers(String) - Method in class ann4j.Neuron

For each observer in the observerList, call the update function of that observer, passing in the info and this neuron, which will be typecasted later.

notifyObservers(String) - Method in interface ann4j.Observable

Notify all observers of a change in the subject.

numberOfInputNeurons - Static variable in class ann4j.parameter

numberOfOutputNeurons - Static variable in class ann4j.parameter

O

Observable - Interface in ann4j

observableList - Variable in class ann4j.NeuronObserver

Observer - Interface in ann4j

observerList - Variable in class ann4j.Neuron

outputLayer - Variable in class ann4j.LayerManager

OutputLayer - Class in ann4j

OutputLayer(int) - Constructor for class ann4j.OutputLayer

outputLayerLength - Variable in class ann4j.MNISTDataBaseFileReader

OutputLayerNeuronBehaviour - Class in ann4j

P

parameter - Class in ann4j

parameter() - Constructor for class ann4j.parameter

printConfusionMatrix() - Method in class ann4j.Trainer

This function prints the confusion matrix of the model

printConfusionMatrix(InputFileReader) - Method in class ann4j.ModelEvaluator

It prints the confusion matrix

printWeights() - Method in class ann4j.Layer

It prints the weights of the neurons

R

readLineToDoubleArray() - Method in class ann4j.MNISTDataBaseFileReader

It reads the next line of the file, splits it into an array of strings, and then converts that array of strings into an array of doubles

rectify(double) - Static method in class ann4j.parameter

registerObserver(Observer) - Method in class ann4j.Neuron

registerObserver(Observer) - Method in interface ann4j.Observable

Register an observer to be notified when the data changes.

relevance - Variable in class ann4j.Neuron

relevancePropagate() - Method in class ann4j.Layer

This function iterates through the list of neurons and calls the relevancePropagate method on each neuron

relevancePropagate() - Method in class ann4j.Neuron

The function `relevancePropagate()` is called on the `myBehaviour` object, which is of type `Behaviour`, and the `this` object is passed as an argument

relevancePropagate(int, int) - Method in class ann4j.LayerManager

The function takes in the layer number and the neuron number of the output layer and then calculates the relevance of each pixel in the input layer

relevancePropagate(int, int) - Method in class ann4j.Trainer

This function propagates relevance from the output layer to the input layer

relevancePropagate(Neuron) - Method in class ann4j.HiddenLayerNeuronBehaviour

relevancePropagate(Neuron) - Method in class ann4j.InputLayerNeuronBehaviour

relevancePropagate(Neuron) - Method in interface ann4j.NeuronBehaviour

This function propagates the relevance from the output layer to the input layer

relevancePropagate(Neuron) - Method in class ann4j.OutputLayerNeuronBehaviour

relu(double) - Static method in class ann4j.NN

If the number is greater than 0, return the number.

reset() - Method in class ann4j.ModelEvaluator

This function resets the confusion matrix, the correct counter, and the turns counter

resetConfusionMatrix() - Method in class ann4j.ModelEvaluator

restart() - Method in class ann4j.InputFileReader

This function restarts the file reader.

restart() - Method in class ann4j.MNISTDataBaseFileReader

rightConnections - Variable in class ann4j.Neuron

rightNeuron - Variable in class ann4j.Connection

S

setActivation(double) - Method in class ann4j.Neuron

This function sets the activation of the neuron to the value passed in as a parameter

setBatchsize(int) - Static method in class ann4j.parameter

setBehaviour() - Method in class ann4j.HiddenLayer

setBehaviour() - Method in class ann4j.InputLayer

setBehaviour() - Method in class ann4j.Layer

The setBehaviour() function is an abstract function that is used to set the behaviour of the animal.

setBehaviour() - Method in class ann4j.OutputLayer

setBehaviour(NeuronBehaviour) - Method in class ann4j.Neuron

This function sets the behaviour of the neuron to the behaviour passed in as a parameter.

setBias() - Static method in class ann4j.NN

This function returns a random number between 0 and 0.1

setBiasLearningRate(double) - Static method in class ann4j.parameter

This function sets the learning rate for the bias

setDelta() - Method in class ann4j.Neuron

The delta difference of the neuron in layer has been changed

setDelta(Neuron) - Method in class ann4j.HiddenLayerNeuronBehaviour

setDelta(Neuron) - Method in class ann4j.InputLayerNeuronBehaviour

setDelta(Neuron) - Method in interface ann4j.NeuronBehaviour

This function sets the delta value of the neuron

setDelta(Neuron) - Method in class ann4j.OutputLayerNeuronBehaviour

setEpsillion(double) - Static method in class ann4j.parameter

This function sets the epsillion value to the value passed in

setExpectedOutputArray(ArrayList<Double>) - Method in class ann4j.LayerManager

This function takes an ArrayList of Doubles as an argument and sets the ExpectedOutputArrayList variable to the argument

setFile(String) - Static method in class ann4j.Writer

setInput(ArrayList<Double>) - Method in class ann4j.InputLayer

This is setting the activation of each neuron in the input layer to the corresponding value in the input array

setInputLayer(ArrayList<Double>) - Method in class ann4j.LayerManager

This function takes an ArrayList of Doubles and sets the inputLayer's input to that ArrayList

setLayerArray(int...) - Static method in class ann4j.parameter

setLayerNum(int) - Method in class ann4j.Layer

This function sets the layer number for each neuron in the layer

setLayerNum(int) - Method in class ann4j.Neuron

This function sets the layer number of the neuron

setLearningRate(double) - Static method in class ann4j.parameter

This function sets the learning rate of the neural network

setModel(LayerManager) - Method in class ann4j.NeuronObserver

This function sets the model to be observed.

setNeuronNum(int) - Method in class ann4j.Neuron

This function sets the number of neurons in the layer

setNeuronNumberToBeTestedinRelavancePropagation(double) - Static method in class ann4j.parameter

setNeuronNumberToBeTestedinRelavancePropagation(Double) - Static method in class ann4j.LayerManager

This function sets the number of neurons to be tested in relevance propagation

setOutputFile(String, boolean) - Static method in class ann4j.parameter

It sets the output file and enables/disables printing in console.

setPrintInConsoleEnabled(boolean) - Static method in class ann4j.Writer

It sets the value of the static variable printInConsole to the value of the parameter bool.

setRectificationFunction(String) - Static method in class ann4j.parameter

This function sets the rectification function to be used in the network

setTestingaccuracy(double) - Method in class ann4j.ModelEvaluator

This function sets the testing accuracy of the model

setTestingFileReader(InputFileReader) - Static method in class ann4j.parameter

setTestingFileReader(String, String) - Static method in class ann4j.parameter

It sets the testing file reader to the required file reader.

setTrainingaccuracy(double) - Method in class ann4j.ModelEvaluator

This function sets the training accuracy of the model

setTrainingFileReader(InputFileReader) - Static method in class ann4j.parameter

setTrainingFileReader(String, String) - Static method in class ann4j.parameter

sigmoid(double) - Static method in class ann4j.NN

The sigmoid function takes a number and returns a number between 0 and 1

singleFileReader - Variable in class ann4j.MNISTDataBaseFileReader

softplus(double) - Static method in class ann4j.NN

The softplus function is a smooth approximation of the rectifier function

T

tanh(double) - Static method in class ann4j.NN

The tanh function takes a number and returns the hyperbolic tangent of that number

test(int) - Method in class ann4j.Trainer

Used to test the model.

testingFileReader - Variable in class ann4j.Trainer

toString() - Method in class ann4j.Connection

This function returns a string that contains the neuron numbers of the neurons that are connected by this connection, as well as the weight of the connection

toString() - Method in class ann4j.Layer

This function returns a string that contains the layer number, the length of the list of neurons, and the toString() function of each neuron in the list of neurons

toString() - Method in class ann4j.LayerManager

This function returns a string representation of the neural network

toString() - Method in class ann4j.Neuron

The toString() function returns a string representation of the object

train() - Method in class ann4j.Trainer

The function takes in an input layer and an expected output layer, and then it uses the input layer to predict the expected output layer

train(int, int) - Method in class ann4j.Trainer

The function trains the neural network by reading the training data from the mnist database and updating the weights and biases of the neural network

Trainer - Class in ann4j

Trainer() - Constructor for class ann4j.Trainer

trainingFileReader - Variable in class ann4j.Trainer

U

update(String, Observable) - Method in class ann4j.NeuronObserver

The update function is called when the observable object is changed

update(String, Observable) - Method in interface ann4j.Observer

The update function is called when the observable object is changed.

updateConfusionMatrix(ArrayList<Double>, int) - Method in class ann4j.ModelEvaluator

This function updates the confusion matrix by comparing the expected output array with the predicted output array

updateConfusionMatrix(ArrayList<Double>, ArrayList<Double>) - Method in class ann4j.ModelEvaluator

This function takes in two arrays, one of expected outputs and one of actual outputs, and updates the confusion matrix accordingly __ __ __ __ |TP FP | 0 1 |FN TN | 2 3

updatePredictionData(double, double, double) - Method in class ann4j.ModelEvaluator

This function updates the prediction data

W

write(Object...) - Static method in class ann4j.Writer

It takes in a variable number of arguments and prints them out

writeln(Object...) - Static method in class ann4j.Writer

Writer - Class in ann4j

Writer() - Constructor for class ann4j.Writer

A B C D E F G H I L M N O P R S T U W
All Classes and Interfaces|All Packages