|
DeepBeliefNetwork Class |
Deep Belief Network.
Inheritance HierarchySystemObject
Accord.NeuroNetwork
Accord.NeuroActivationNetwork
Accord.Neuro.NetworksDeepBeliefNetwork
Accord.NeuroNetwork
Accord.NeuroActivationNetwork
Accord.Neuro.NetworksDeepBeliefNetwork
Namespace: Accord.Neuro.Networks
Assembly: Accord.Neuro (in Accord.Neuro.dll) Version: 3.8.0
SyntaxThe DeepBeliefNetwork type exposes the following members.
Constructors| Name | Description | |
|---|---|---|
 | DeepBeliefNetwork(Int32, RestrictedBoltzmannMachine) |
Creates a new DeepBeliefNetwork.
|
| DeepBeliefNetwork(Int32, Int32) |
Creates a new DeepBeliefNetwork.
|
| DeepBeliefNetwork(IStochasticFunction, Int32, Int32) |
Creates a new DeepBeliefNetwork.
|
Properties| Name | Description | |
|---|---|---|
 | InputsCount |
Network's inputs count.
(Inherited from Network.) |
| Layers |
Network's layers.
(Inherited from Network.) |
| Machines |
Gets the Restricted Boltzmann Machines
on each layer of this deep network.
|
| Output |
Network's output vector.
(Inherited from Network.) |
| OutputCount |
Gets the number of output neurons in the network
(the size of the computed output vectors).
|
Methods| Name | Description | |
|---|---|---|
| Compute(Double) |
Computes the network's outputs for a given input.
(Overrides NetworkCompute(Double).) |
| Compute(Double, Int32) |
Computes the network's outputs for a given input.
|
 | CreateGaussianBernoulli |
Creates a Gaussian-Bernoulli network.
|
| CreateMixedNetwork |
Creates a Mixed-Bernoulli network.
|
| 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.) |
| GenerateInput |
Samples an input vector from the network
given an output vector.
|
| GenerateOutput(Double) |
Samples an output vector from the network
given an input vector.
|
| GenerateOutput(Double, Int32) |
Samples an output vector from the network
given an input vector.
|
| GetHashCode | Serves as the default hash function. (Inherited from Object.) |
| GetType | Gets the Type of the current instance. (Inherited from Object.) |
| Load(Stream) |
Loads a network from a stream.
|
| Load(String) |
Loads a network from a file.
|
| MemberwiseClone | Creates a shallow copy of the current Object. (Inherited from Object.) |
| Pop |
Removes the last layer from the network.
|
| Push(Int32) |
Inserts a new layer at the end of this network.
|
| Push(RestrictedBoltzmannMachine) |
Stacks a new Boltzmann Machine at the end of this network.
|
| Push(Int32, IStochasticFunction) |
Inserts a new layer at the end of this network.
|
| Push(Int32, IStochasticFunction, IStochasticFunction) |
Inserts a new layer at the end of this network.
|
| Randomize |
Randomize layers of the network.
(Inherited from Network.) |
| Reconstruct(Double) |
Reconstructs a input vector for a given output.
|
| Reconstruct(Double, Int32) |
Reconstructs a input vector using the output
vector of a given layer.
|
| Save(Stream) |
Saves the network to a stream.
|
| Save(String) |
Saves the network to a stream.
|
| SetActivationFunction |
Set new activation function for all neurons of the network.
(Inherited from ActivationNetwork.) |
| ToString | Returns a string that represents the current object. (Inherited from Object.) |
| UpdateVisibleWeights |
Updates the weights of the visible layers by copying
the reverse of the weights in the hidden layers.
|
Fields| Name | Description | |
|---|---|---|
 | inputsCount |
Network's inputs count.
(Inherited from Network.) |
| layers |
Network's layers.
(Inherited from Network.) |
| layersCount |
Network's layers count.
(Inherited from Network.) |
| output |
Network's output vector.
(Inherited from Network.) |
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.) |
Remarks
The Deep Belief Network can be seen as a collection of stacked
Restricted Boltzmann
Machines disposed as layers of a network. In turn, the
whole network can be seen as an stochastic activation network
in which the neurons activate within some given probability.
See Also