Package | Description |
---|---|
deepnetts.net |
Neural network architectures with their corresponding builders.
|
deepnetts.net.loss |
Commonly used loss functions, which are used to calculate error during the training as a difference between predicted and target output.
|
Modifier and Type | Method and Description |
---|---|
LossFunction |
NeuralNetwork.getLossFunction()
Returns a loss function of this network, which is used to calculate total network error during the training.
|
Modifier and Type | Method and Description |
---|---|
void |
NeuralNetwork.setLossFunction(LossFunction lossFunction)
Sets a loss function of this network, which is used to calculate total network error during the training.
|
Modifier and Type | Method and Description |
---|---|
ConvolutionalNetwork.Builder |
ConvolutionalNetwork.Builder.lossFunction(Class<? extends LossFunction> clazz) |
Modifier and Type | Class and Description |
---|---|
class |
BinaryCrossEntropyLoss
Cross Entropy Loss is a loss function used for binary classification tasks (two classes, single output which represents probability ).
|
class |
CrossEntropyLoss
Average Cross Entropy Loss function commonly used for multi class classification problems.
|
class |
MeanSquaredErrorLoss
Mean Squared Error Loss function.
|
Copyright © 2022. All rights reserved.