A C D E F I J L N P R S T

A

Attribute - Class in com.github.mrdimosthenis.synapses

The attribute a codec can have.

Attribute(String, boolean) - Constructor for class com.github.mrdimosthenis.synapses.Attribute

C

Codec - Class in com.github.mrdimosthenis.synapses

The constructors and methods of codecs.

Codec(Attribute[], Stream<Map<String, String>>) - Constructor for class com.github.mrdimosthenis.synapses.Codec

Creates a codec by consuming a stream of data points.

Codec(String) - Constructor for class com.github.mrdimosthenis.synapses.Codec

Creates a codec by parsing its JSON representation.

com.github.mrdimosthenis.synapses - package com.github.mrdimosthenis.synapses

D

decode(double[]) - Method in class com.github.mrdimosthenis.synapses.Codec

Decodes a data point.

Documentation - Class in com.github.mrdimosthenis.synapses

Synapses-java is a neural networks library for Java!

Documentation() - Constructor for class com.github.mrdimosthenis.synapses.Documentation

E

encode(Map<String, String>) - Method in class com.github.mrdimosthenis.synapses.Codec

Encodes a data point.

errors(double[], double[], boolean) - Method in class com.github.mrdimosthenis.synapses.Net

F

fit(double, double[], double[]) - Method in class com.github.mrdimosthenis.synapses.Net

Adjust the weights of the neural network to the provided observation.

fitPar(double, double[], double[]) - Method in class com.github.mrdimosthenis.synapses.Net

Adjust the weights of the neural network to the provided observation.

flag - Variable in class com.github.mrdimosthenis.synapses.Attribute

The flag of the attribute defines whether it is discrete or not.

Fun - Class in com.github.mrdimosthenis.synapses

The activation functions a neuron can have.

I

IDENTITY - Static variable in class com.github.mrdimosthenis.synapses.Fun

Identity is a linear function where the output is equal to the input.

J

json() - Method in class com.github.mrdimosthenis.synapses.Codec

The JSON representation of the codec.

json() - Method in class com.github.mrdimosthenis.synapses.Net

The JSON representation of the neural network.

L

LEAKY_RE_LU - Static variable in class com.github.mrdimosthenis.synapses.Fun

LeakyReLU gives a small proportion of x if x is negative and x otherwise.

N

name - Variable in class com.github.mrdimosthenis.synapses.Attribute

The name of the attribute.

Net - Class in com.github.mrdimosthenis.synapses

The constructors and methods of neural networks.

Net(int[], IntFunction<Fun>, IntFunction<Double>) - Constructor for class com.github.mrdimosthenis.synapses.Net

Creates a neural network.

Net(int[]) - Constructor for class com.github.mrdimosthenis.synapses.Net

Creates a random neural network.

Net(int[], Long) - Constructor for class com.github.mrdimosthenis.synapses.Net

Creates a non-random neural network.

Net(String) - Constructor for class com.github.mrdimosthenis.synapses.Net

Cretaes a neural network by parsing its JSON representation.

P

parPredict(double[]) - Method in class com.github.mrdimosthenis.synapses.Net

Makes a prediction for the provided input.

predict(double[]) - Method in class com.github.mrdimosthenis.synapses.Net

Makes a prediction for the provided input.

R

rmse(Stream<double[][]>) - Static method in class com.github.mrdimosthenis.synapses.Stats

Root Mean Square Error.

S

score(Stream<double[][]>) - Static method in class com.github.mrdimosthenis.synapses.Stats

Classification Accuracy.

SIGMOID - Static variable in class com.github.mrdimosthenis.synapses.Fun

Sigmoid takes any real value as input and outputs values in the range of 0 to 1.

Stats - Class in com.github.mrdimosthenis.synapses

Measure the difference between the values predicted by a neural network and the observed values.

Stats() - Constructor for class com.github.mrdimosthenis.synapses.Stats

svg() - Method in class com.github.mrdimosthenis.synapses.Net

An SVG representation of the neural network.

T

TANH - Static variable in class com.github.mrdimosthenis.synapses.Fun

Tanh is similar to Sigmoid, but outputs values in the range of -1 and 1.

A C D E F I J L N P R S T