public class DBM extends RBM
RBM
Constructor and Description |
---|
DBM(String[] options)
DBM - Create a DBM with 'options' (we use WEKA-style option processing).
|
Modifier and Type | Method and Description |
---|---|
RBM[] |
getRBMs() |
Jama.Matrix[] |
getWs() |
double[] |
prob_z(double[] z)
Hidden Activation Probability - returns P(z|x) where p(z[i]==1|x) for each element.
|
double[][] |
prob_Z(double[][] X_)
Hidden Activation Probability - returns P(Z|X).
|
void |
setH(int H) |
void |
setH(int[] h)
Set hidden layers specification
|
void |
setH(int H,
int N)
SetH -
|
void |
setH(int H,
int L,
int N)
SetH - for a discriminative DBM (where the last h == L)
|
double |
train(double[][] X_)
Train - Setup and train the RBM on X, over m_E epochs.
|
double |
train(double[][] X_,
int batchSize)
Train - Setup and batch-train the RBM on X.
|
void |
update(double[][] X_)
Update - On raw data (with no bias column)
|
void |
update(Jama.Matrix X)
Update - Carry out one epoch of CD, update W.
|
void |
update(Jama.Matrix X,
double s)
Update - Carry out one epoch of CD, update W.
|
calculateError, epoch, getE, getH, getLearningRate, getMomentum, getOptions, getW, initWeights, main, makeW, makeW, prob_x, prob_X, prob_Z, propUp, sample_epoch, sample_x, sample_X, sample_z, sample_Z, setE, setLearningRate, setMomentum, setOptions, setSeed, toString, train, update, update
protected RBM[] rbm
protected int[] h
public RBM[] getRBMs()
public double[] prob_z(double[] z)
RBM
public double[][] prob_Z(double[][] X_)
RBM
public void setH(int[] h)
public void setH(int H, int L, int N)
H
- hidden layersL
- output linear layerN
- number of hidden layerspublic void setH(int H, int N)
H
- hidden layersN
- number of hidden layerspublic double train(double[][] X_) throws Exception
RBM
public double train(double[][] X_, int batchSize) throws Exception
RBM
public void update(Jama.Matrix X)
RBM
public void update(Jama.Matrix X, double s)
RBM
Copyright © 2017. All Rights Reserved.