Layer

java.lang.Object
- smile.base.mlp.Layer

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

HiddenLayer, OutputLayer
```
public abstract class Layer
extends java.lang.Object
implements java.io.Serializable
```
A layer in the neural network.

See Also:

Serialized Form

Field Summary

Fields
Modifier and Type	Field and Description
`protected double[]`	`bias` The bias.
`protected java.lang.ThreadLocal<double[]>`	`biasGradient` The bias gradient.
`protected java.lang.ThreadLocal<double[]>`	`biasUpdate` The bias update.
`protected int`	`n` The number of neurons in this layer
`protected java.lang.ThreadLocal<double[]>`	`output` The output vector.
`protected java.lang.ThreadLocal<double[]>`	`outputGradient` The output gradient.
`protected int`	`p` The number of input variables.
`protected java.lang.ThreadLocal<double[]>`	`rmsBiasGradient` The accumulate bias gradient.
`protected java.lang.ThreadLocal<smile.math.matrix.Matrix>`	`rmsWeightGradient` The accumulate weight gradient.
`protected smile.math.matrix.Matrix`	`weight` The affine transformation matrix.
`protected java.lang.ThreadLocal<smile.math.matrix.Matrix>`	`weightGradient` The weight gradient.
`protected java.lang.ThreadLocal<smile.math.matrix.Matrix>`	`weightUpdate` The weight update.

Constructor Summary

Constructors
Constructor and Description

Layer(int n, int p)
Constructor.

Layer(smile.math.matrix.Matrix weight, double[] bias)
Constructor.

Constructors
Constructor and Description
`Layer(int n, int p)` Constructor.
`Layer(smile.math.matrix.Matrix weight, double[] bias)` Constructor.

Method Summary

All Methods Static Methods Instance Methods Abstract Methods Concrete Methods
Modifier and Type	Method and Description
`abstract void`	`backpropagate(double[] lowerLayerGradient)` Propagates the errors back to a lower layer.
`void`	`computeGradient(double[] x)` Computes the parameter gradient for a sample of (mini-)batch.
`void`	`computeGradientUpdate(double[] x, double learningRate, double momentum, double decay)` Computes the parameter gradient and update the weights.
`abstract void`	`f(double[] x)` The activation or output function.
`int`	`getInputSize()` Returns the dimension of input vector (not including bias value).
`int`	`getOutputSize()` Returns the dimension of output vector.
`double[]`	`gradient()` Returns the output gradient vector.
`static HiddenLayerBuilder`	`linear(int n)` Returns a hidden layer with linear activation function.
`static OutputLayerBuilder`	`mle(int n, OutputFunction f)` Returns an output layer with (log-)likelihood cost function.
`static OutputLayerBuilder`	`mse(int n, OutputFunction f)` Returns an output layer with mean squared error cost function.
`double[]`	`output()` Returns the output vector.
`void`	`propagate(double[] x)` Propagates signals from a lower layer to this layer.
`static HiddenLayerBuilder`	`rectifier(int n)` Returns a hidden layer with rectified linear activation function.
`static HiddenLayerBuilder`	`sigmoid(int n)` Returns a hidden layer with sigmoid activation function.
`static HiddenLayerBuilder`	`tanh(int n)` Returns a hidden layer with hyperbolic tangent activation function.
`void`	`update(int m, double learningRate, double momentum, double decay, double rho, double epsilon)` Adjust network weights by back-propagation algorithm.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - n
```
protected int n
```
    The number of neurons in this layer
  - p
```
protected int p
```
    The number of input variables.
  - weight
```
protected smile.math.matrix.Matrix weight
```
    The affine transformation matrix.
  - bias
```
protected double[] bias
```
    The bias.
  - output
```
protected transient java.lang.ThreadLocal<double[]> output
```
    The output vector.
  - outputGradient
```
protected transient java.lang.ThreadLocal<double[]> outputGradient
```
    The output gradient.
  - weightGradient
```
protected transient java.lang.ThreadLocal<smile.math.matrix.Matrix> weightGradient
```
    The weight gradient.
  - biasGradient
```
protected transient java.lang.ThreadLocal<double[]> biasGradient
```
    The bias gradient.
  - rmsWeightGradient
```
protected transient java.lang.ThreadLocal<smile.math.matrix.Matrix> rmsWeightGradient
```
    The accumulate weight gradient.
  - rmsBiasGradient
```
protected transient java.lang.ThreadLocal<double[]> rmsBiasGradient
```
    The accumulate bias gradient.
  - weightUpdate
```
protected transient java.lang.ThreadLocal<smile.math.matrix.Matrix> weightUpdate
```
    The weight update.
  - biasUpdate
```
protected transient java.lang.ThreadLocal<double[]> biasUpdate
```
    The bias update.
- Constructor Detail
  - Layer
```
public Layer(int n,
             int p)
```
    Constructor. Randomly initialized weights and zero bias.
    
    Parameters:
    
    n - the number of neurons.
    
    p - the number of input variables (not including bias value).
  - Layer
```
public Layer(smile.math.matrix.Matrix weight,
             double[] bias)
```
    Constructor.
    
    Parameters:
    
    weight - the weight matrix.
    
    bias - the bias vector.
- Method Detail
  - getOutputSize
```
public int getOutputSize()
```
    Returns the dimension of output vector.
  - getInputSize
```
public int getInputSize()
```
    Returns the dimension of input vector (not including bias value).
  - output
```
public double[] output()
```
    Returns the output vector.
  - gradient
```
public double[] gradient()
```
    Returns the output gradient vector.
  - propagate
```
public void propagate(double[] x)
```
    Propagates signals from a lower layer to this layer.
    
    Parameters:
    
    x - the lower layer signals.
  - f
```
public abstract void f(double[] x)
```
    The activation or output function.
    
    Parameters:
    
    x - the input and output values.
  - backpropagate
```
public abstract void backpropagate(double[] lowerLayerGradient)
```
    Propagates the errors back to a lower layer.
    
    Parameters:
    
    lowerLayerGradient - the gradient vector of lower layer.
  - computeGradientUpdate
```
public void computeGradientUpdate(double[] x,
                                  double learningRate,
                                  double momentum,
                                  double decay)
```
    Computes the parameter gradient and update the weights.
    
    Parameters:
    
    x - the input vector.
    
    learningRate - the learning rate.
    
    momentum - the momentum factor
    
    decay - weight decay factor
  - computeGradient
```
public void computeGradient(double[] x)
```
    Computes the parameter gradient for a sample of (mini-)batch.
    
    Parameters:
    
    x - the input vector.
  - update
```
public void update(int m,
                   double learningRate,
                   double momentum,
                   double decay,
                   double rho,
                   double epsilon)
```
    Adjust network weights by back-propagation algorithm.
    
    Parameters:
    
    m - the size of mini-batch.
    
    learningRate - the learning rate.
    
    momentum - the momentum factor
    
    decay - weight decay factor
  - linear
```
public static HiddenLayerBuilder linear(int n)
```
    Returns a hidden layer with linear activation function.
    
    Parameters:
    
    n - the number of neurons.
  - rectifier
```
public static HiddenLayerBuilder rectifier(int n)
```
    Returns a hidden layer with rectified linear activation function.
    
    Parameters:
    
    n - the number of neurons.
  - sigmoid
```
public static HiddenLayerBuilder sigmoid(int n)
```
    Returns a hidden layer with sigmoid activation function.
    
    Parameters:
    
    n - the number of neurons.
  - tanh
```
public static HiddenLayerBuilder tanh(int n)
```
    Returns a hidden layer with hyperbolic tangent activation function.
    
    Parameters:
    
    n - the number of neurons.
  - mse
```
public static OutputLayerBuilder mse(int n,
                                     OutputFunction f)
```
    Returns an output layer with mean squared error cost function.
    
    Parameters:
    
    n - the number of neurons.
    
    f - the output function.
  - mle
```
public static OutputLayerBuilder mle(int n,
                                     OutputFunction f)
```
    Returns an output layer with (log-)likelihood cost function.
    
    Parameters:
    
    n - the number of neurons.
    
    f - the output function.

Class Layer

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

n

p

weight

bias

output

outputGradient

weightGradient

biasGradient

rmsWeightGradient

rmsBiasGradient

weightUpdate

biasUpdate

Constructor Detail

Layer

Layer

Method Detail

getOutputSize

getInputSize

output

gradient

propagate

f

backpropagate

computeGradientUpdate

computeGradient

update

linear

rectifier

sigmoid

tanh

mse

mle