All Packages  Class Hierarchy  This Package  Previous  Next  Index

Class sim.funApp.LookupTable

java.lang.Object
   |
   +----sim.funApp.FunApp
           |
           +----sim.funApp.LookupTable

public class LookupTable
extends FunApp
A standard lookup table of n elements (weights). IMPORTANT NOTES AND REMINDERS: 1) dEdOut must be a single element MatrixD object. 2) There should not be a "bias". This is not a neural network. 3) There should be a 3 tuple passed as a parameter to this object for each dimension of the lookup table. The first element is the minimum value, followed by the maximum value, and finally the discretization factor (the number of elements in that dimension). 4) It is not necessary for the inputs to be rounded to discrete values before being passed to this object. The object will discretize the inputs automatically. The input vector is treated as being a vector of indices to the lookup table. Any index that is below or above the minimum or maximum index for that dimension will be clipped. 5) The formula for calculating an index for a given input variable a is: floor[(n(a-min))/(max-min)] where n is the number of elements for this dimension. 6) Hessian calculations are not yet implemented.

This code is (c) 1997 Mance Harmon <harmonme@aa.wpafb.af.mil>, http://www.aa.wpafb.af.mil/~harmonme
The source and object code may be redistributed freely. If the code is modified, please state so in the comments.

Version:
2.0, 8 May 97
Author:
Mance Harmon, Leemon Baird

Constructor Index

 o LookupTable()

Method Index

 o BNF(int)
 o clone()
Make an exact duplicate of this class.
 o cloneVars(FunApp)
After making a copy of self during a clone(), call cloneVars() to copy variables into the copy, then return super.cloneVars(copy).
 o evaluate()
calculate the output for the given input
 o findGradients()
Calculate the output and gradient for a given input.
 o findHessian()
Calculate the output, gradient, and Hessian for a given input.
 o nWeights(int, int)
Return # elements (weights) in the lookup table.
 o parse(Parser, int)
Parse the input file to get the parameters for this object.
 o setIO(MatrixD, MatrixD, MatrixD, MatrixD, MatrixD, MatrixD, MatrixD, MatrixD, MatrixD)
Define the MatrixD objects that will be used by evaluate() and findGradients().
 o unparse(Unparser, int)
Output a description of this object that can be parsed with parse().

Constructors

 o LookupTable
 public LookupTable()

Methods

 o setIO
 public void setIO(MatrixD inVect,
                   MatrixD outVect,
                   MatrixD weights,
                   MatrixD dEdIn,
                   MatrixD dEdOut,
                   MatrixD dEdWeights,
                   MatrixD dEdIndIn,
                   MatrixD dEdOutdOut,
                   MatrixD dEdWeightsdWeights) throws MatrixException
Define the MatrixD objects that will be used by evaluate() and findGradients(). All 6 should be column vectors (n by 1 matrices). All the MatrixD objects are copied, but the pointers still point to the same data arrays.

Throws: MatrixException
if vector shapes don't match
Overrides:
setIO in class FunApp
 o evaluate
 public void evaluate()
calculate the output for the given input

Overrides:
evaluate in class FunApp
 o findGradients
 public void findGradients()
Calculate the output and gradient for a given input. This does everything evaluate() does, plus it calculates the gradient of the error with respect to the inputs and weights, dEdx and dEdw, User must set dEdOut before calling.

Overrides:
findGradients in class FunApp
 o findHessian
 public void findHessian()
Calculate the output, gradient, and Hessian for a given input. This does everything evaluate() and findGradients() do, plus it calculates the Hessian of the error with resepect to the the weights and inputs, dEdxdx, dEdwdx, and dEdwdw.

Overrides:
findHessian in class FunApp
 o nWeights
 public int nWeights(int nIn,
                     int nOut)
Return # elements (weights) in the lookup table.

Overrides:
nWeights in class FunApp
 o BNF
 public String BNF(int lang)
Overrides:
BNF in class FunApp
 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 FunApp
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 FunApp
 o clone
 public Object clone()
Make an exact duplicate of this class. For objects it contains, it only duplicates the pointers, not the objects they point to. For a new FunApp called MyFunApp, the code in this method should be the single line: return cloneVars(new MyFunApp());

Overrides:
clone in class FunApp
 o cloneVars
 public Object cloneVars(FunApp copy)
After making a copy of self during a clone(), call cloneVars() to copy variables into the copy, then return super.cloneVars(copy). The variables copied are just those set in parse() and setWatchManager(). The caller will be required to call setIO to set up the rest of the variables.

Overrides:
cloneVars in class FunApp

All Packages  Class Hierarchy  This Package  Previous  Next  Index