| Package | Description |
|---|---|
| hex.deeplearning |
| Modifier and Type | Class and Description |
|---|---|
static class |
Neurons.Input
Input layer of the Neural Network
This layer is different from other layers as it has no incoming weights,
but instead gets its activation values from the training points.
|
static class |
Neurons.Linear
Output neurons for regression - Softmax
|
static class |
Neurons.Maxout
Maxout neurons
|
static class |
Neurons.MaxoutDropout
Maxout neurons with dropout
|
static class |
Neurons.Output
Abstract class for Output neurons
|
static class |
Neurons.Rectifier
Rectifier linear unit (ReLU) neurons
|
static class |
Neurons.RectifierDropout
Rectifier linear unit (ReLU) neurons with dropout
|
static class |
Neurons.Softmax
Output neurons for classification - Softmax
|
static class |
Neurons.Tanh
Tanh neurons - most common, most stable
|
static class |
Neurons.TanhDropout
Tanh neurons with dropout
|
| Modifier and Type | Field and Description |
|---|---|
Neurons |
Neurons._input |
Neurons |
Neurons._previous
References for feed-forward connectivity
|
| Modifier and Type | Method and Description |
|---|---|
static Neurons[] |
DeepLearningTask.makeNeuronsForTesting(DeepLearningModel.DeepLearningModelInfo minfo) |
static Neurons[] |
DeepLearningTask.makeNeuronsForTraining(DeepLearningModel.DeepLearningModelInfo minfo) |
| Modifier and Type | Method and Description |
|---|---|
void |
Neurons.init(Neurons[] neurons,
int index,
DeepLearning p,
DeepLearningModel.DeepLearningModelInfo minfo,
boolean training)
Initialization of the parameters and connectivity of a Neuron layer
|
static void |
DeepLearningTask.step(long seed,
Neurons[] neurons,
DeepLearningModel.DeepLearningModelInfo minfo,
boolean training,
double[] responses) |
Copyright © 2013–2014 0xdata. All rights reserved.