public class LossFunctions extends Object
Modifier and Type | Class and Description |
---|---|
static class |
LossFunctions.LossFunction
MSE: Mean Squared Error: Linear Regression
EXPLL: Exponential log likelihood: Poisson Regression
XENT: Cross Entropy: Binary Classification
SOFTMAX: Softmax Regression
RMSE_XENT: RMSE Cross Entropy
|
Constructor and Description |
---|
LossFunctions() |
Modifier and Type | Method and Description |
---|---|
static double |
reconEntropy(INDArray input,
INDArray hBias,
INDArray vBias,
INDArray W,
ActivationFunction activationFunction)
Reconstruction entropy for Denoising AutoEncoders and RBMs
|
static double |
score(INDArray labels,
LossFunctions.LossFunction lossFunction,
INDArray output,
double l2,
boolean useRegularization)
Generic scoring function
|
public static double score(INDArray labels, LossFunctions.LossFunction lossFunction, INDArray output, double l2, boolean useRegularization)
labels
- the labels to scorelossFunction
- the loss function to useoutput
- the output functionl2
- the l2 coefficientuseRegularization
- whether to use regularizationpublic static double reconEntropy(INDArray input, INDArray hBias, INDArray vBias, INDArray W, ActivationFunction activationFunction)
input
- the input ndarrayhBias
- the hidden bias of the neural networkvBias
- the visible bias of the neural networkW
- the weight matrix of the neural networkCopyright © 2014. All Rights Reserved.