Package dk.alexandra.fresco.stat.mlp
Class Layer
Object
Layer
- All Implemented Interfaces:
DRes<Layer>
public class Layer extends Object implements DRes<Layer>
Instances of this class represents fully connected layers in a neural network. Instances are
immutable.
-
Constructor Summary
Constructors Constructor Description Layer(double[][] weights, double[] bias, ProtocolBuilderNumeric inputBuilder)
Create a new fully connected layer with the given weights and biases and using a sigmoid activation function.Layer(double[][] weights, double[] bias, ProtocolBuilderNumeric inputBuilder, ActivationFunction activationFunction)
Create a new fully connected layer with the given open weights, biases and activation function.Layer(int in, int out, Random prng, ProtocolBuilderNumeric inputBuilder)
Layer(int in, int out, Random prng, ProtocolBuilderNumeric inputBuilder, ActivationFunction activationFunction)
Create a new layer with random weights (bias is zero and weights are distributed as a standard Gaussian distribution divided by the number of neurons.Layer(Matrix<DRes<SFixed>> weights, ArrayList<DRes<SFixed>> bias, ActivationFunction activationFunction)
Create a new fully connected layer with the given secret weights, biases and activation function. -
Method Summary
Modifier and Type Method Description ArrayList<DRes<SFixed>>
getBias()
Matrix<DRes<SFixed>>
getWeights()
Layer
out()
-
Constructor Details
-
Layer
public Layer(Matrix<DRes<SFixed>> weights, ArrayList<DRes<SFixed>> bias, ActivationFunction activationFunction)Create a new fully connected layer with the given secret weights, biases and activation function. -
Layer
public Layer(double[][] weights, double[] bias, ProtocolBuilderNumeric inputBuilder, ActivationFunction activationFunction)Create a new fully connected layer with the given open weights, biases and activation function. -
Layer
public Layer(double[][] weights, double[] bias, ProtocolBuilderNumeric inputBuilder)Create a new fully connected layer with the given weights and biases and using a sigmoid activation function. -
Layer
public Layer(int in, int out, Random prng, ProtocolBuilderNumeric inputBuilder, ActivationFunction activationFunction)Create a new layer with random weights (bias is zero and weights are distributed as a standard Gaussian distribution divided by the number of neurons. -
Layer
-
-
Method Details
-
getWeights
public Matrix<DRes<SFixed>> getWeights() -
getBias
-
out
- Specified by:
out
in interfaceDRes<Layer>
-