JMSLTM Numerical Library 5.0.1

com.imsl.datamining.neural
Interface Activation

All Superinterfaces:
Serializable

public interface Activation
extends Serializable

Interface implemented by perceptron activation functions.

Standard activation functions are defined as static members of this interface. New activation functions can be defined by implementing a method, g(double x), returning the value and a method, derivative(double x, double y), returning the derivative of g evaluated at x where y = g(x).

See Also:
Feed Forward Class Example 1, Perceptron

Field Summary
static Activation LINEAR
          The identity activation function, g(x) = x.
static Activation LOGISTIC
          The logistic activation function, g(x)=frac{1}{1+e^{-x}}.
static Activation LOGISTIC_TABLE
          The logistic activation function computed using a table.
static long serialVersionUID
           
static Activation SOFTMAX
          The softmax activation function.
static Activation SQUASH
          The squash activation function, g(x) = frac{x}{1+|x|}
static Activation TANH
          The hyperbolic tangent activation function, g(x)=tanh{x}=
  frac{e^x-e^{-x}}{e^x+e^{-x}}.
 
Method Summary
 double derivative(double x, double y)
          Returns the value of the derivative of the activation function.
 double g(double x)
          Returns the value of the activation function.
 

Field Detail

LINEAR

static final Activation LINEAR
The identity activation function, g(x) = x.


LOGISTIC

static final Activation LOGISTIC
The logistic activation function, g(x)=frac{1}{1+e^{-x}}.


LOGISTIC_TABLE

static final Activation LOGISTIC_TABLE
The logistic activation function computed using a table. This is an approximation to the logistic function that is faster to compute.

This version of the logistic function differs from the exact version by at most 4.0e-9.

Networks trained using this activation should not use Activation.LOGISTIC for forecasting. Forecasting should be done using the specific function supplied during training.


serialVersionUID

static final long serialVersionUID
See Also:
Constant Field Values

SOFTMAX

static final Activation SOFTMAX
The softmax activation function.

{rm{softmax}}_{rm{i}}=frac{{{mathop{rm e}nolimits} ^{Z_i } }}
  {{sumlimits_{j = 1}^C {e^{Z_j } } }}

.


SQUASH

static final Activation SQUASH
The squash activation function, g(x) = frac{x}{1+|x|}


TANH

static final Activation TANH
The hyperbolic tangent activation function, g(x)=tanh{x}=
  frac{e^x-e^{-x}}{e^x+e^{-x}}.

Method Detail

derivative

double derivative(double x,
                  double y)
Returns the value of the derivative of the activation function.

Parameters:
x - A double which specifies the point at which the activation function is to be evaluated.
y - A double which specifies y = g(x), the value of the activation function at x. This parameter is not mathematically required, but can sometimes be used to more quickly compute the derivative.
Returns:
A double containing the value of the derivative of the activation function at x.

g

double g(double x)
Returns the value of the activation function.

Parameters:
x - A double is the point at which the activation function is to be evaluated.
Returns:
A double containing the value of the activation function at x.

JMSLTM Numerical Library 5.0.1

Copyright © 1970-2008 Visual Numerics, Inc.
Built July 8 2008.