Layer

java.lang.Object
- water.Iced
- - hex.Layer

All Implemented Interfaces:

java.lang.Cloneable, Freezable

Direct Known Subclasses:

Layer.Input, Layer.Maxout, Layer.Output, Layer.Rectifier, Layer.Tanh
```
public abstract class Layer
extends Iced
```
Neural network layer.

Nested Class Summary

Nested Classes
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.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`

Field Summary

Fields
Modifier and Type	Field and Description
`protected double[]`	`_a`
`protected double[]`	`_b`
`protected double[]`	`_bm`
`protected double[]`	`_e`
`protected Layer`	`_previous`
`protected float[]`	`_w`
`protected float[]`	`_wm`
`static DocGen.FieldDoc[]`	`DOC_FIELDS`
`NeuralNet.InitialWeightDistribution`	`initial_weight_distribution`
`double`	`initial_weight_scale`
`double`	`l1`
`double`	`l2`
`double`	`max_w2`
`static double`	`missing_double_value`
`static int`	`missing_int_value` We need a way to encode a missing value in the neural net forward/back-propagation scheme.
`long`	`momentum_ramp`
`double`	`momentum_stable`
`double`	`momentum_start`
`double`	`rate`
`double`	`rate_annealing`
`double`	`rate_decay`
`int`	`units`

Constructor Summary

Constructors
Constructor and Description

Layer()

Constructors
Constructor and Description
`Layer()`

Method Summary

Methods
Modifier and Type	Method and Description
`protected abstract void`	`bprop()`
`Layer`	`clone()`
`void`	`close()`
`protected abstract void`	`fprop(boolean training)`
`void`	`init(Layer[] ls, int index, boolean weights)`
`void`	`init(Layer[] ls, int index, NeuralNet p)`
`double`	`momentum(long n)`
`double`	`rate(long n)`
`static void`	`shareWeights(Layer[] src, Layer[] dst)`
`static void`	`shareWeights(Layer src, Layer dst)`
`void`	`transferParams(Layer p)`
`void`	`transferParams(NeuralNet p)`
`AutoBuffer`	`writeJSON(AutoBuffer bb)`

Methods inherited from class water.Iced
frozenType, init, newInstance, read, toDocField, write, writeJSONFields

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

DOC_FIELDS

public static DocGen.FieldDoc[] DOC_FIELDS

units
```
public int units
```

initial_weight_distribution

public NeuralNet.InitialWeightDistribution initial_weight_distribution

initial_weight_scale
```
public double initial_weight_scale
```

rate
```
public double rate
```

rate_decay
```
public double rate_decay
```

rate_annealing
```
public double rate_annealing
```

l1
```
public double l1
```

l2
```
public double l2
```

momentum_start
```
public double momentum_start
```

momentum_ramp
```
public long momentum_ramp
```

momentum_stable
```
public double momentum_stable
```

max_w2
```
public double max_w2
```

_w
```
protected transient float[] _w
```

_b
```
protected transient double[] _b
```

_a
```
protected transient double[] _a
```

_e
```
protected transient double[] _e
```

_wm
```
protected transient float[] _wm
```

_bm
```
protected transient double[] _bm
```

_previous
```
protected transient Layer _previous
```

missing_int_value
```
public static final int missing_int_value
```
We need a way to encode a missing value in the neural net forward/back-propagation scheme. For simplicity and performance, we simply use the largest values to encode a missing value. If we run into exactly one of those values with regular neural net updates, then we're very likely also running into overflow problems, which will trigger a NaN somewhere, which will be caught and lead to automatic job cancellation.

See Also:
Constant Field Values

missing_double_value
```
public static final double missing_double_value
```
See Also:
Constant Field Values

Constructor Detail
- Layer
```
public Layer()
```

Method Detail

transferParams

public void transferParams(NeuralNet p)

transferParams
```
public void transferParams(Layer p)
```

init

public final void init(Layer[] ls,
        int index,
        NeuralNet p)

init

public void init(Layer[] ls,
        int index,
        boolean weights)

close
```
public void close()
```

fprop

protected abstract void fprop(boolean training)

bprop
```
protected abstract void bprop()
```

rate
```
public double rate(long n)
```

momentum
```
public double momentum(long n)
```

clone
```
public Layer clone()
```
Overrides:

clone in class Iced

shareWeights

public static void shareWeights(Layer src,
                Layer dst)

shareWeights

public static void shareWeights(Layer[] src,
                Layer[] dst)

writeJSON

public AutoBuffer writeJSON(AutoBuffer bb)

Overrides:: writeJSON in class Iced

Class Layer

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class water.Iced

Methods inherited from class java.lang.Object

Field Detail

DOC_FIELDS

units

initial_weight_distribution

initial_weight_scale

rate

rate_decay

rate_annealing

l1

l2

momentum_start

momentum_ramp

momentum_stable

max_w2

_w

_b

_a

_e

_wm

_bm

_previous

missing_int_value

missing_double_value

Constructor Detail

Layer

Method Detail

transferParams

transferParams

init

init

close

fprop

bprop

rate

momentum

clone

shareWeights

shareWeights

writeJSON