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 double[]`	`gradient` The gradient vector.
`protected int`	`n` The number of neurons in this layer
`protected double[]`	`output` The output vector.
`protected int`	`p` The number of input variables.
`protected smile.math.matrix.Matrix`	`update` The weight update of mini batch or momentum.
`protected double[]`	`updateBias` The bias update of mini batch or momentum.
`protected smile.math.matrix.Matrix`	`weight` The affine transformation matrix.

Constructor Summary

Constructors
Constructor and Description

Layer(int n, int p)
Constructor.

Constructors
Constructor and Description
`Layer(int n, int p)` Constructor.

Method Summary

All Methods Static Methods Instance Methods Abstract Methods Concrete Methods
Modifier and Type	Method and Description
`abstract void`	`backpropagate(double[] error)` Propagates the errors back to a lower layer.
`void`	`computeUpdate(double eta, double alpha, double[] x)` Computes the updates of weight.
`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 error/gradient vector.
`static smile.base.mlp.HiddenLayerBuilder`	`linear(int n)` Returns a hidden layer with linear activation function.
`static smile.base.mlp.OutputLayerBuilder`	`mle(int n, OutputFunction f)` Returns an output layer with (log-)likelihood cost function.
`static smile.base.mlp.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 smile.base.mlp.HiddenLayerBuilder`	`rectifier(int n)` Returns a hidden layer with rectified linear activation function.
`static smile.base.mlp.HiddenLayerBuilder`	`sigmoid(int n)` Returns a hidden layer with sigmoid activation function.
`static smile.base.mlp.HiddenLayerBuilder`	`tanh(int n)` Returns a hidden layer with hyperbolic tangent activation function.
`void`	`update(double alpha, double lambda)` 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.
  - output
```
protected double[] output
```
    The output vector.
  - gradient
```
protected double[] gradient
```
    The gradient vector.
  - weight
```
protected smile.math.matrix.Matrix weight
```
    The affine transformation matrix.
  - update
```
protected smile.math.matrix.Matrix update
```
    The weight update of mini batch or momentum.
  - bias
```
protected double[] bias
```
    The bias.
  - updateBias
```
protected double[] updateBias
```
    The bias update of mini batch or momentum.
- Constructor Detail
  - Layer
```
public Layer(int n,
             int p)
```
    Constructor.
    
    Parameters:
    
    n - the number of neurons.
    
    p - the number of input variables (not including bias value).
- 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 error/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[] error)
```
    Propagates the errors back to a lower layer.
    
    Parameters:
    
    error - the gradient vector of lower layer.
  - computeUpdate
```
public void computeUpdate(double eta,
                          double alpha,
                          double[] x)
```
    Computes the updates of weight.
    
    Parameters:
    
    eta - the learning rate.
    
    alpha - the momentum factor
    
    x - the input vector.
  - update
```
public void update(double alpha,
                   double lambda)
```
    Adjust network weights by back-propagation algorithm.
    
    Parameters:
    
    alpha - the momentum factor
    
    lambda - weight decay factor
  - linear
```
public static smile.base.mlp.HiddenLayerBuilder linear(int n)
```
    Returns a hidden layer with linear activation function.
    
    Parameters:
    
    n - the number of neurons.
  - rectifier
```
public static smile.base.mlp.HiddenLayerBuilder rectifier(int n)
```
    Returns a hidden layer with rectified linear activation function.
    
    Parameters:
    
    n - the number of neurons.
  - sigmoid
```
public static smile.base.mlp.HiddenLayerBuilder sigmoid(int n)
```
    Returns a hidden layer with sigmoid activation function.
    
    Parameters:
    
    n - the number of neurons.
  - tanh
```
public static smile.base.mlp.HiddenLayerBuilder tanh(int n)
```
    Returns a hidden layer with hyperbolic tangent activation function.
    
    Parameters:
    
    n - the number of neurons.
  - mse
```
public static smile.base.mlp.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 smile.base.mlp.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

output

gradient

weight

update

bias

updateBias

Constructor Detail

Layer

Method Detail

getOutputSize

getInputSize

output

gradient

propagate

f

backpropagate

computeUpdate

update

linear

rectifier

sigmoid

tanh

mse

mle