All Packages  Class Hierarchy  This Package  Previous  Next  Index

Class sim.errFun.LocalLearning

java.lang.Object
   |
   +----sim.errFun.ErrFun
           |
           +----sim.errFun.LocalLearning

public class LocalLearning
extends ErrFun
Perform local learning with the given data (only looks at input data) Gradient descent is performed on interference, I(x,x'), where x and x' are chosen randomly from the training data with the exception that x and x' never represent the same sample (otherwise interference couldn't be reduced for that error surface produced by x=x').

This code is (c) 1996 Leemon Baird <leemon@cs.cmu.edu>, http://www.cs.cmu.edu/~baird
The source and object code may be redistributed freely. If the code is modified, please state so in the comments.

Version:
1.09, 23 July 97
Author:
Leemon Baird, Mance Harmon, Scott Weaver

Variable Index

 o D
 o data
the input/output pairs for the training set
 o incremental
the mode of learning: incremental or epoch-wise
 o interference
pointer to interference
 o N

Constructor Index

 o LocalLearning()

Method Index

 o BNF(int)
Return the BNF description of how to parse the parameters of this object.
 o evaluate(Random, boolean, boolean, boolean)
return the scalar output for the current weight vector x
 o findGradient()
update the fGradient vector based on the dEdOutput
 o getGradient()
The gradient of f(x) with respect to x (a column vector) this should override ErrFun.java which returns dEdWeights by default
 o initialize(int)
Initialize, either partially or completely.
 o parse(Parser, int)
Parse the input file to get the parameters for this object.
 o setWatchManager(WatchManager, String)
Register all variables with this WatchManager.
 o unparse(Unparser, int)
Output a description of this object that can be parsed with parse().

Variables

 o data
 protected Data data
the input/output pairs for the training set

 o incremental
 protected boolean incremental
the mode of learning: incremental or epoch-wise

 o N
 protected double N
 o D
 protected double D
 o interference
 protected PDouble interference
pointer to interference

Constructors

 o LocalLearning
 public LocalLearning()

Methods

 o setWatchManager
 public void setWatchManager(WatchManager wm,
                             String name)
Register all variables with this WatchManager. This will be called after all parsing is done. setWatchManager should be overridden and forced to call the same method on all the other objects in the experiment.

Overrides:
setWatchManager in class ErrFun
 o BNF
 public String BNF(int lang)
Return the BNF description of how to parse the parameters of this object.

Overrides:
BNF in class ErrFun
 o unparse
 public void unparse(Unparser u,
                     int lang)
Output a description of this object that can be parsed with parse().

Overrides:
unparse in class ErrFun
See Also:
Parsable
 o parse
 public Object parse(Parser p,
                     int lang) throws ParserException
Parse the input file to get the parameters for this object.

Throws: ParserException
parser didn't find the required token
Overrides:
parse in class ErrFun
 o getGradient
 public MatrixD getGradient()
The gradient of f(x) with respect to x (a column vector) this should override ErrFun.java which returns dEdWeights by default

Overrides:
getGradient in class ErrFun
 o evaluate
 public double evaluate(Random rnd,
                        boolean willFindDeriv,
                        boolean willFindHess,
                        boolean rememberNoise)
return the scalar output for the current weight vector x

Overrides:
evaluate in class ErrFun
 o findGradient
 public void findGradient()
update the fGradient vector based on the dEdOutput

Overrides:
findGradient in class ErrFun
 o initialize
 public void initialize(int level)
Initialize, either partially or completely.

Overrides:
initialize in class ErrFun
See Also:
initialize

All Packages  Class Hierarchy  This Package  Previous  Next  Index