Resilient Backpropagation method for unconstrained optimization.
Inheritance Hierarchy Namespace: Accord.Math.OptimizationAccord.Math (in Accord.Math.dll) Version: 3.8.0
Syntaxpublic class ResilientBackpropagation : BaseGradientOptimizationMethod, IGradientOptimizationMethod, IOptimizationMethod, IOptimizationMethod<double[], double>, IGradientOptimizationMethod<double[], double>, IFunctionOptimizationMethod<double[], double>
Public Class ResilientBackpropagation Inherits BaseGradientOptimizationMethod Implements IGradientOptimizationMethod, IOptimizationMethod, IOptimizationMethod(Of Double(), Double), IGradientOptimizationMethod(Of Double(), Double), IFunctionOptimizationMethod(Of Double(), Double)Request Example View Source
The ResilientBackpropagation type exposes the following members.
Constructors Properties Name Description DecreaseFactorGets the decrease parameter, also referred as eta minus. Default is 0.5.
FunctionGets or sets the function to be optimized.
(Inherited from BaseOptimizationMethod.) GradientGets or sets a function returning the gradient vector of the function to be optimized for a given value of its free parameters.
(Inherited from BaseGradientOptimizationMethod.) IncreaseFactorGets the increase parameter, also referred as eta plus. Default is 1.2.
IterationsGets or sets the maximum number of iterations performed by the learning algorithm.
NumberOfVariablesGets the number of variables (free parameters) in the optimization problem.
(Inherited from BaseOptimizationMethod.) SolutionGets the current solution found, the values of the parameters which optimizes the function.
(Inherited from BaseOptimizationMethod.) TokenGets or sets a cancellation token that can be used to stop the learning algorithm while it is running.
(Inherited from BaseOptimizationMethod.) ToleranceGets or sets the maximum change in the average log-likelihood after an iteration of the algorithm used to detect convergence.
UpdateLowerBoundGets or sets the minimum possible update step, also referred as delta max. Default is 1e-6.
UpdateUpperBoundGets or sets the maximum possible update step, also referred as delta min. Default is 50.
ValueGets the output of the function at the current
Solution.
(Inherited from BaseOptimizationMethod.) Top Methods Events Name Description ProgressChangedOccurs when the current learning progress has changed.
Top Extension Methods Name Description HasMethodChecks whether an object implements a method with the given name.
(Defined by ExtensionMethods.) IsEqualCompares 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 See AlsoRetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4