| Interface | Description |
|---|---|
| InputPreProcessor |
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| Class | Description |
|---|---|
| ComputationGraphConfiguration |
ComputationGraphConfiguration is a configuration object for neural networks with arbitrary connection structure.
|
| ComputationGraphConfiguration.GraphBuilder | |
| ComputationGraphConfigurationTest | |
| ComputationGraphConfigurationTest.StaticInnerGraphVertex | |
| MultiLayerConfiguration |
Configuration for a multi layer network
|
| MultiLayerConfiguration.Builder | |
| MultiLayerNeuralNetConfigurationTest |
Created by agibsonccc on 11/27/14.
|
| MultiNeuralNetConfLayerBuilderTest | |
| NeuralNetConfiguration |
A Serializable configuration
for neural nets that covers per layer parameters
|
| NeuralNetConfiguration.Builder | |
| NeuralNetConfiguration.ListBuilder |
Fluent interface for building a list of configurations
|
| NeuralNetConfigurationTest |
Created by agibsonccc on 11/27/14.
|
| ReflectionsHelper |
Original credit:
https://gist.github.com/nonrational/287ed109bb0852f982e8
|
| Enum | Description |
|---|---|
| BackpropType |
Defines the type of backpropagation.
|
| ConvolutionMode |
ConvolutionMode defines how convolution operations should be executed for Convolutional and Subsampling layers,
for a given input size and network configuration (specifically stride/padding/kernel sizes).
Currently, 3 modes are provided: Strict: Output size for Convolutional and Subsampling layers are calculated as follows, in each dimension: outputSize = (inputSize - kernelSize + 2*padding) / stride + 1. |
| GradientNormalization |
Gradient normalization strategies.
|
| LearningRatePolicy |
Learning Rate Policy
How to decay learning rate during training.
|
| Updater |
All the possible different updaters
|