Click or drag to resize
Accord.NET (logo) Accord.Neuro.Learning Namespace
Contains neural network learning algorithms such as the Levenberg-Marquardt (LM) with Bayesian Regularization and the Resilient Backpropagation (RProp) for multi-layer networks. This namespace extends the AForge.Neuro namespace of the AForge.NET project.
Classes
  ClassDescription
Public classBackPropagationLearning
Back propagation learning algorithm.
Public classContrastiveDivergenceLearning
Contrastive Divergence learning algorithm for Restricted Boltzmann Machines.
Public classDeepBeliefNetworkLearning
Deep Belief Network learning algorithm.
Public classDeepNeuralNetworkLearning
Deep Neural Network learning algorithm.
Public classDeltaRuleLearning
Delta rule learning algorithm.
Public classElasticNetworkLearning
Elastic network learning algorithm.
Public classEvolutionaryLearning
Neural networks' evolutionary learning algorithm, which is based on Genetic Algorithms.
Public classLevenbergMarquardtLearning
Levenberg-Marquardt Learning Algorithm with optional Bayesian Regularization.
Public classCode exampleParallelResilientBackpropagationLearning
Resilient Backpropagation learning algorithm.
Public classPerceptronLearning
Perceptron learning algorithm.
Public classResilientBackpropagationLearning
Resilient Backpropagation learning algorithm.
Public classSOMLearning
Kohonen Self Organizing Map (SOM) learning algorithm.
Interfaces
  InterfaceDescription
Public interfaceISupervisedLearning
Supervised learning interface.
Public interfaceIUnsupervisedLearning
Unsupervised learning interface.
Delegates
  DelegateDescription
Public delegateActivationNetworkLearningConfigurationFunction
Delegate used to configure and create layer-specific learning algorithms.
Public delegateRestrictedBoltzmannNetworkLearningConfigurationFunction
Delegate used to configure and create layer-specific learning algorithms.
Enumerations
  EnumerationDescription
Public enumerationJacobianMethod
The Jacobian computation method used by the Levenberg-Marquardt.