All Packages  Class Hierarchy  This Package  Previous  Next  Index

Class sim.funApp.Net

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

public class Net

extends FunApp

This code is (c) 1997 Scott E. Weaver <scott.weaver@uc.edu>, http://http://www.ececs.uc.edu/~sweaver
The source and object code may be redistributed freely provided no fee is charged. If the code is modified, please state so in the comments.

Version:

1.05, 19 Sep 97 possibly fixed parse bug, verified second derivitives. -Scott Weaver If you'd like you can check this code for your particular application see comment block at the end of this file. The variables have a specific convention. dSikdwik means derivative of the single node Sik with respect to the vector wik. The derivitive of this variable with respect to Simo would be dSikdwikdSimo. imo means the i minus one'th layer. ik means the ith layer and the kth node in layer i. A variable that ends in T stands for Transpose. 'u' refers to weights in all layers following (but not including) the current layer. 'w' refers to weights in the current layer. Variables of the form d?* stands for derrivitive of ? wrt *, where ? and * are usually variables defined elsewhere Comments with a number such as (4) or 5 or |2| refer to my personal notes - Scott Weaver

Author:

Scott Weaver, Leemon Baird

Net()

BNF(int)

Return the BNF description of how to parse the parameters of this object.

clone()

Make an exact duplicate of this class.

cloneVars(FunApp)

After making a copy of self during a clone(), call cloneVars() to copy variables into the copy, then return super.cloneVars(copy).

evaluate()

calculate the output for the given input.

findGradients()

Calculate the output and gradient for a given input.

findHessian()

Calculate the output, gradient, and Hessian for a given input.

nWeights(int, int)

Return # weights needed for nIn inputs (including the first one which is always 1.0), and nOut outputs.

parse(Parser, int)

Parse the input file to get the parameters for this object.

setIO(Matrix, Matrix, Matrix, Matrix, Matrix, Matrix, Matrix, Matrix, Matrix)

Define the Matrix objects that will be used by evaluate() and findGradients().

unparse(Unparser, int)

Output a description of this object that can be parsed with parse().

 public Net()

 public void setIO(Matrix inVect,
                   Matrix outVect,
                   Matrix weights,
                   Matrix dEdIn,
                   Matrix dEdOut,
                   Matrix dEdWeights,
                   Matrix dEdIndIn,
                   Matrix dEdOutdOut,
                   Matrix dEdWeightsdWeights) throws MatrixException

Define the Matrix objects that will be used by evaluate() and findGradients(). All 9 should be column vectors (n by 1 matrices). All the Matrix 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

 public void evaluate()

calculate the output for the given input. Also calculates Ap and App because it is appropriate to do so eventhough they are not used until backward pass

Overrides:

evaluate in class FunApp

 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 resepect to the the weights and inputs, dEdx, and dEdw. User must set dEdOut before calling.

Overrides:

findGradients in class FunApp

 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. User must set dEdOut and dEdOutdOut before calling.

Overrides:

findHessian in class FunApp

 public int nWeights(int nIn,
                     int nOut)

Return # weights needed for nIn inputs (including the first one which is always 1.0), and nOut outputs.

Overrides:

nWeights in class FunApp

 public String BNF(int lang)

Return the BNF description of how to parse the parameters of this object.

Overrides:

BNF in class FunApp

 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

 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

 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

 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