ELUVector class

Applies the Exponential Linear Unit (ELU) activation function over a given input of type Tensor<Vector>. In contrast to the standard ReLU function, this function has a small negative value for negative inputs, which can help prevent the dying ReLU problem and speed up learning by pushing the mean activation closer to zero.

The function is defined as f(x) = x if x > 0, and f(x) = alpha * (e^x - 1) if x <= 0. The value of alpha dictates the multiplier for negative inputs and is set to 1.0 by default. The calculation is handled via the eluVector math operation.

Example:

Tensor<Vector> v = Tensor<Vector>([-1.0, 0.0, 1.0]);
ELUVector elu = ELUVector(alpha: 1.0);
Tensor<Vector> out = elu(v);

Implemented types

• ActivationFunction<Vector>

Constructors

ELUVector({double alpha = 1.0})

Properties

alpha ↔ double

getter/setter pair

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

call(Tensor<Vector> input) → Tensor<Vector>

override

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited