StochasticNeuron Class

Stochastic Activation Neuron.

Inheritance Hierarchy

SystemObject
  Accord.NeuroNeuron
    Accord.NeuroActivationNeuron
      Accord.Neuro.NeuronsStochasticNeuron

Namespace: Accord.Neuro.Neurons
Assembly: Accord.Neuro (in Accord.Neuro.dll) Version: 3.8.0

Syntax

Copy

[SerializableAttribute]
public class StochasticNeuron : ActivationNeuron

<SerializableAttribute>
Public Class StochasticNeuron
	Inherits ActivationNeuron

Request Example View Source

The StochasticNeuron type exposes the following members.

Constructors

	Name	Description
	StochasticNeuron	Initializes a new instance of the StochasticNeuron class.

Top

Properties

	Name	Description
	ActivationFunction	Gets or sets the stochastic activation function for this stochastic neuron.
	InputsCount	Neuron's inputs count. (Inherited from Neuron.)
	Output	Neuron's output value. (Inherited from Neuron.)
	RandGenerator	Random number generator. (Inherited from Neuron.)
	Sample	Gets the neuron sample value generated in the last call of any of the Generate(Double) methods.
	Threshold	Threshold value. (Inherited from ActivationNeuron.)
	Weights	Neuron's weights. (Inherited from Neuron.)

Top

Methods

	Name	Description
	Compute	Computes output value of neuron. (Overrides ActivationNeuronCompute(Double).)
	Equals	Determines whether the specified object is equal to the current object. (Inherited from Object.)
	Finalize	Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.)
	Generate(Double)	Samples the neuron output considering the stochastic activation function.
	Generate(Double)	Samples the neuron output considering the stochastic activation function.
	GetHashCode	Serves as the default hash function. (Inherited from Object.)
	GetType	Gets the Type of the current instance. (Inherited from Object.)
	MemberwiseClone	Creates a shallow copy of the current Object. (Inherited from Object.)
	Randomize	Randomize neuron. (Inherited from ActivationNeuron.)
	ToString	Returns a string that represents the current object. (Inherited from Object.)

Top

Fields

	Name	Description
	function	Activation function. (Inherited from ActivationNeuron.)
	inputsCount	Neuron's inputs count. (Inherited from Neuron.)
	output	Neuron's output value. (Inherited from Neuron.)
	rand	Random number generator. (Inherited from Neuron.)
	threshold	Threshold value. (Inherited from ActivationNeuron.)
	weights	Neuron's weights. (Inherited from Neuron.)

Top

Extension Methods

	Name	Description
	HasMethod	Checks whether an object implements a method with the given name. (Defined by ExtensionMethods.)
	IsEqual	Compares two objects for equality, performing an elementwise comparison if the elements are vectors or matrices. (Defined by Matrix.)
	To(Type)	Overloaded. Converts an object into another type, irrespective of whether the conversion can be done at compile time or not. This can be used to convert generic types to numeric types during runtime. (Defined by ExtensionMethods.)
	ToT	Overloaded. Converts an object into another type, irrespective of whether the conversion can be done at compile time or not. This can be used to convert generic types to numeric types during runtime. (Defined by ExtensionMethods.)

Top

Remarks

The Stochastic Activation Neuron is an activation neuron which activates (returns 1) only within a given probability. The neuron has a random component in the activation function, and the neuron fires only if the total sum, after applied to a logistic activation function, is greater than a randomly sampled value.

Reference

Accord.Neuro.Neurons Namespace