Layer class abstract

Base super-class for any layer of NeuralNetwork

Implementers

• Dense
• Input
• LayerNormalization

Constructors

Layer(int units, String? name, {bool trainable = true, bool useBiases = true})

Properties

activatedDerivativeBuffer ↔ List<Matrix>?

Derivatives of the activation function used in the learning process

getter/setter pair

b ↔ Matrix?

Matrix.column of the biases of the Layer

getter/setter pair

hashCode → int

The hash code for this object.

no setter, inherited

inputDataBuffer ↔ Matrix?

Input data buffer used in the learning proccess

getter/setter pair

name ↔ String?

The name of the layer

getter/setter pair

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

trainable ↔ bool

Identify if this is trainable

getter/setter pair

units ↔ int

Number of rows in output Matrix.column after activation (or applying) of the Layer over input data

getter/setter pair

useBiases → bool

Defines if train biases or keep them as zero vector

final

w ↔ Matrix?

Matrix of the weights of the Layer

getter/setter pair

wasInitialized ↔ bool

Identify if initialization was called

getter/setter pair

Methods

act(dynamic inputs, {bool train = false}) → Matrix

Apply Layer's logic to the inputs

clear() → void

After-training method, typically clear buffered data from the training process

init([dynamic parametr]) → void

Initialization of Layer's parametrs should be called before calling (act()) the Layer

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