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
-
D
-
-
data
- the input/output pairs for the training set
-
incremental
- the mode of learning: incremental or epoch-wise
-
interference
- pointer to interference
-
N
-
-
LocalLearning()
-
-
BNF(int)
- Return the BNF description of how to parse the parameters of this object.
-
evaluate(Random, boolean, boolean, boolean)
- return the scalar output for the current weight vector x
-
findGradient()
- update the fGradient vector based on the dEdOutput
-
getGradient()
- The gradient of f(x) with respect to x (a column vector)
this should override ErrFun.java which returns dEdWeights by default
-
initialize(int)
- Initialize, either partially or completely.
-
parse(Parser, int)
- Parse the input file to get the parameters for this object.
-
setWatchManager(WatchManager, String)
- Register all variables with this WatchManager.
-
unparse(Unparser, int)
- Output a description of this object that can be parsed with parse().
data
protected Data data
- the input/output pairs for the training set
incremental
protected boolean incremental
- the mode of learning: incremental or epoch-wise
N
protected double N
D
protected double D
interference
protected PDouble interference
- pointer to interference
LocalLearning
public LocalLearning()
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
BNF
public String BNF(int lang)
- Return the BNF description of how to parse the parameters of this object.
- Overrides:
- BNF in class ErrFun
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
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
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
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
findGradient
public void findGradient()
- update the fGradient vector based on the dEdOutput
- Overrides:
- findGradient in class ErrFun
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