Layer<N extends num, E, T extends Signal<N, E, T> , S extends Scale<N> > class
Base class for ANN layers.
- Implementers
Constructors
- Layer.fromJson(dynamic json)
-
factory
Properties
-
activationFunction
→ ActivationFunction<
N, E> -
final
-
asLayerHidden
→ LayerHidden<
N, E, T, S> -
no setter
-
asLayerInput
→ LayerInput<
N, E, T, S> -
no setter
-
asLayerOutput
→ LayerOutput<
N, E, T, S> -
no setter
- format → String
-
The signal format of this Layer.
no setter
-
gradients
→ List<
T> -
no setter
- hashCode → int
-
The hash code for this object.
no setterinherited
- hasNextLayer → bool
-
no setter
- layerType → String
-
no setter
- length → int
-
no setter
- neurons → T
-
no setter
-
nextLayer
→ Layer<
N, E, T, S> ? -
no setter
-
previousGradients
→ List<
T> -
no setter
-
previousLayer
→ Layer<
N, E, T, S> ? -
no setter
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
-
weights
→ List<
T> -
no setter
- withBiasNeuron → bool
-
final
Methods
-
activateLayer(
) → void -
connectTo(
Layer< N, E, T, S> nextLayer, {Random? random, List<T> ? weights}) → void -
getNeurons(
) → List< N> -
getNeuronsAsDouble(
) → List< double> -
getNeuronsAsString(
) → List< String> -
getNeuronsDenormalized(
S scale) → List< N> -
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
resetGradients(
) → void -
resetLayer(
) → void -
resetNetwork(
) → void -
resetNextLayerNetwork(
) → void -
resetWeights(
[Random? rand]) → void -
setNeurons(
T signal) → void -
toJson(
{bool withIndent = false}) → String - Converts to an encoded JSON.
-
toJsonMap(
) → Map< String, dynamic> - Converts this Layer to a JSON Map.
-
toString(
) → String -
A string representation of this object.
override
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited