ActivationFunction

```
public interface ActivationFunction
```
The activation function in hidden layers.

Method Summary

All Methods Static Methods Instance Methods Abstract Methods Default Methods
Modifier and Type	Method and Description
`void`	`f(double[] x)` The output function.
`void`	`g(double[] g, double[] y)` The gradient function.
`static ActivationFunction`	`linear()` Linear/Identity function.
`java.lang.String`	`name()` Returns the name of activation function.
`static ActivationFunction`	`rectifier()` The rectifier activation function max(0, x).
`static ActivationFunction`	`sigmoid()` Logistic sigmoid function: sigmoid(v)=1/(1+exp(-v)).
`static ActivationFunction`	`tanh()` Hyperbolic tangent activation function.

- Method Detail
  - name
```
java.lang.String name()
```
    Returns the name of activation function.
  - f
```
void f(double[] x)
```
    The output function.
    
    Parameters:
    
    x - the input vector.
  - g
```
void g(double[] g,
       double[] y)
```
    The gradient function.
    
    Parameters:
    
    g - the gradient vector. On input, it holds W'*g, where W and g are the weight matrix and gradient of upper layer, respectively. On output, it is the gradient of this layer.
    
    y - the output vector.
  - linear
```
static ActivationFunction linear()
```
    Linear/Identity function.
  - rectifier
```
static ActivationFunction rectifier()
```
    The rectifier activation function max(0, x). It is introduced with strong biological motivations and mathematical justifications. The rectifier is the most popular activation function for deep neural networks. A unit employing the rectifier is called a rectified linear unit (ReLU).
  - sigmoid
```
static ActivationFunction sigmoid()
```
    Logistic sigmoid function: sigmoid(v)=1/(1+exp(-v)). For multi-class classification, each unit in output layer corresponds to a class. For binary classification and cross entropy error function, there is only one output unit whose value can be regarded as posteriori probability.
  - tanh
```
static ActivationFunction tanh()
```
    Hyperbolic tangent activation function. The tanh function is a rescaling of the logistic sigmoid, such that its outputs range from -1 to 1.

Interface ActivationFunction

Method Summary

Method Detail

name

f

g

linear

rectifier

sigmoid

tanh