|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectclarion.common.BPNet
clarion.nacs.AMNet
Field Summary |
Fields inherited from class clarion.common.BPNet |
BLAT, BLDT, BLPT, BLRT, debug, DesiredOutput, Errors, Eta, Hidden, HiddenDeriv, HiddenErrors, HiddenMomentum, HiddenThresholds, HiddenToOutputMomentum, HiddenToOutputWeights, HINITTHRESHOLD, HINITWEIGHT, HtoOWeights, Input, InputToHiddenMomentum, InputToHiddenWeights, ItoHWeights, LINITTHRESHOLD, LINITWEIGHT, Momentum, nHidden, nInput, NM, nOutput, Output, OutputDeriv, OutputMomentum, OutputThresholds, PM, RZero, SUCC_C3, SUCC_C4, succRate, sumSqErrors |
Constructor Summary | |
AMNet(int nIdx,
Global g,
GKS gks)
new constructor, # of input nodes should be equal to # of output nodes. |
|
AMNet(int inputNum,
int hiddenNum,
int outputNum,
int dNum,
int[] dValNums)
|
|
AMNet(int inputNum,
int hiddenNum,
int outputNum,
int dNum,
short[] dValNums)
|
Method Summary | |
void |
getOutput(double[] arr)
Returns the output in terms of one dimensional array after filtering noise. |
void |
getOutput(double[][] arr)
Returns the output in terms of two dimensional array after filtering noise. |
Feature[] |
getOutputFeatures(boolean multiFlag)
Returns the output in terms of features. |
Feature[] |
getResults()
Returns the retrieval results in terms of features. |
int |
getRT()
Returns the response time. |
void |
reinit()
reinitialization routine. |
void |
resetRT()
reset the response time. |
boolean |
retrieval(boolean multiFlag)
the retrieval process. |
void |
setAssocAssimOn(boolean flag)
Sets the flag for assimulation or not. |
void |
setDesiredOutput(Feature[] features)
Sets the desired output with the specific features. |
void |
setDesiredOutput(short[] arr)
Deprecated. Replcaced by setOutput( short[][] arr ). |
void |
setDesiredOutput(short[][] arr)
Sets the desired output with the specific info of active values of a chunk in terms of two dimensional array. |
void |
setInput(double[][] arr)
Sets the input with the specific info of activation of a chunk in terms of two dimensional array. |
void |
setInput(Feature[] features)
Sets the input with the specific features. |
void |
setInput(int[] arr)
Deprecated. Replcaced by setInput( short[][] arr ). |
void |
setInput(short[][] arr)
Sets the input with the specific info of active values of a chunk in terms of two dimensional array. |
void |
setInput(short[][][] arr)
Sets the input with the specific info of active values of chunks in terms of three dimensional array. |
void |
setNoiseThreshold(double th)
Sets noise threshold. |
void |
setPassNum(int num)
|
void |
training()
the assimulation (training) process. |
void |
update()
update the AMN. |
Methods inherited from class clarion.common.BPNet |
backwardPass, calcRT, computeErrors, computeHiddenActivation, computeHiddenErrors, computeOutputActivation, forwardPass, getInput, getnHidden, getnInput, getNM, getnOutput, getOutput, getOutput, getOutput, getOutput, getPM, getResponseTime, getSuccRate, getSumSqErrors, modifyHiddenToOutput, modifyInputToHidden, reinitWeights, resetMatches, restoreInitWeights, setDesiredOutput, setDesiredOutput, setInput, setInput, setLearningRate, setMomentum, updateMatches |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
public AMNet(int inputNum, int hiddenNum, int outputNum, int dNum, int[] dValNums)
public AMNet(int inputNum, int hiddenNum, int outputNum, int dNum, short[] dValNums)
public AMNet(int nIdx, Global g, GKS gks)
nIdx
- the AMN index.g
- the associated global settings.gks
- the associated GKS.Method Detail |
public void reinit()
public Feature[] getResults()
public void getOutput(double[] arr)
getOutput
in class BPNet
arr
- the array to store current output.
public void getOutput(double[][] arr)
public Feature[] getOutputFeatures(boolean multiFlag)
public void resetRT()
public int getRT()
public void setNoiseThreshold(double th)
th
- the value to set the noise threshold.public void setAssocAssimOn(boolean flag)
public void setPassNum(int num)
public void setInput(int[] arr)
setInput
in class BPNet
arr
- the content used as input.public void setInput(short[][] arr)
arr
- the content used as input.public void setInput(double[][] arr)
arr
- the content used as input.public void setInput(short[][][] arr)
arr
- the content used as input.public void setInput(Feature[] features)
features
- the features used as input.public void setDesiredOutput(short[] arr)
setDesiredOutput
in class BPNet
arr
- the content used as output.public void setDesiredOutput(short[][] arr)
arr
- the content used as input.public void setDesiredOutput(Feature[] features)
setDesiredOutput
in class BPNet
features
- the features used as input.public void training()
public boolean retrieval(boolean multiFlag)
multiFlag
- allow multiple active values in one dimension.public void update()
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |