LeakyReLUVector class

Applies leaky ReLu over a given input of type Tensor<Vector>. In contrast to the standard ReLU function, this function multiplies negative values with a small negative number alpha to prevent the dying gradient problem.

The value of alpha dictates the slope of the function for negative inputs and is set to 0.01 by default. The calculation is handled via the leakyReluVector math operation.

Example:

Tensor<Vector> v = Tensor<Vector>([-1.0, 0.0, 1.0]);
LeakyReLUVector leakyRelu = LeakyReLUVector(alpha: 0.02);
Tensor<Vector> out = leakyRelu(v);

Implemented types

• ActivationFunction<Vector>

Constructors

LeakyReLUVector({double alpha = 0.01})

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