| Package | Description |
|---|---|
| hex |
The hex package contains math and machine learning algorithms for H2O.
|
| Modifier and Type | Class and Description |
|---|---|
static class |
Layer.Input |
static class |
Layer.Linear
Linear output layer is used for regression
Rows with missing values in the response column will be ignored
|
static class |
Layer.Maxout |
static class |
Layer.MaxoutDropout |
static class |
Layer.Output |
static class |
Layer.Rectifier |
static class |
Layer.RectifierDropout |
static class |
Layer.RectifierPrime |
static class |
Layer.Softmax
Softmax output layer is used for classification
Rows with missing values in the response column will be ignored
|
static class |
Layer.Tanh |
static class |
Layer.TanhDropout |
static class |
Layer.TanhPrime
Apply tanh to the weights' transpose.
|
static class |
Layer.VecLinear |
static class |
Layer.VecsInput |
static class |
Layer.VecSoftmax |
| Modifier and Type | Field and Description |
|---|---|
protected Layer |
Layer._previous |
Layer[] |
NeuralNet.NeuralNetModel.layers |
| Modifier and Type | Method and Description |
|---|---|
Layer |
Layer.clone() |
Layer |
Layer.VecsInput.clone() |
abstract Layer[] |
Trainer.layers() |
Layer[] |
Trainer.Base.layers() |
Layer[] |
Trainer.Direct.layers() |
Layer[] |
Trainer.Threaded.layers() |
Layer[] |
Trainer.MapReduce.layers() |
Layer[] |
Trainer.OpenCL.layers() |
| Modifier and Type | Method and Description |
|---|---|
static NeuralNet.Errors |
NeuralNet.eval(Layer[] ls,
long n,
long[][] cm) |
static NeuralNet.Errors |
NeuralNet.eval(Layer[] ls,
Vec[] vecs,
Vec resp,
long n,
long[][] cm) |
void |
Layer.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.Input.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.Softmax.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.Linear.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.Tanh.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.TanhPrime.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.Maxout.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.Rectifier.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.RectifierPrime.init(Layer[] ls,
int index,
boolean weights) |
void |
Layer.init(Layer[] ls,
int index,
NeuralNet p) |
static void |
Layer.shareWeights(Layer[] src,
Layer[] dst) |
static void |
Layer.shareWeights(Layer[] src,
Layer[] dst) |
static void |
Layer.shareWeights(Layer src,
Layer dst) |
| Constructor and Description |
|---|
Trainer.Base(Layer[] ls) |
Trainer.Direct(Layer[] ls,
double epochs,
Key job) |
Trainer.MapReduce(Layer[] ls,
double epochs,
Key job) |
Trainer.OpenCL(Layer[] ls) |
Trainer.Threaded(Layer[] ls,
double epochs,
Key job,
int threads) |
Copyright © 2013–2014 0xdata. All rights reserved.