Activations

enum Activations : Enum<Activations>

Neural network hyperparameter, activation function of a node defines the output of that node given an input or set of inputs.

Entries

Sparsemax

Sparsemax()

Sparsemax activation function is similar to softmax but able to output sparse probabilities.

TanhShrink

TanhShrink()

TanhShrink Activation Function.

Snake

Snake()

Snake Activation Function.

LiSHT

LiSHT()

Non-Parametric Linearly Scaled Hyperbolic Tangent (LiSHT) Activation Function.

Gelu

Gelu()

Gelu Function

HardShrink

HardShrink()

HardShrink Function

Mish

Mish()

Mish activation function.

Swish

Swish()

Swish activation function.

SoftShrink

SoftShrink()

Softshrink activation function.

HardSigmoid

HardSigmoid()

Hard sigmoid activation function.

SoftSign

SoftSign()

Softsign activation function.

SoftPlus

SoftPlus()

Softplus activation function.

Exponential

Exponential()

Exponential activation function.

LogSoftmax

LogSoftmax()

Log softmax activation function.

Softmax

Softmax()

Softmax converts a real vector to a vector of categorical probabilities. The elements of the output vector are in range (0, 1) and sum to 1.

Selu

Selu()

Scaled Exponential Linear Unit (SELU).

Elu

Elu()

Exponential Linear Unit.

Relu6

Relu6()

Computes Rectified Linear 6:

Relu

Relu()

Rectified linear unit (ReLU).

Tanh

Tanh()

Hyperbolic tangent activation function.

Sigmoid

Sigmoid()

Sigmoid activation function.

Linear

Linear()

Linear unit. Returns unmodified input.

Types

Companion

object Companion

Properties

name

val name: String

ordinal

val ordinal: Int