SuperNN  1.0.0
Class Hierarchy

Go to the graphical class hierarchy

This inheritance list is sorted roughly, but not completely, alphabetically:
[detail level 123]
 CSuperNN::ActFuncActivation function dispatcher
 CSuperNN::ConnectionSynaptic connection between two neurons
 CSuperNN::ElliotElliot sigmoid-like function
 CSuperNN::ElliotSymmetricElliot sigmoid-like function (Symmetric)
 Cstd::exceptionSTL class
 CSuperNN::ExceptionThe exception can be identified by the type() method
 CSuperNN::GaussianGaussian function
 CSuperNN::GaussianSymmetricGaussian symmetric function
 CSuperNN::NBN::Hist
 CSuperNN::LinearLinear function
 CSuperNN::NetworkArtificial neural network structure that supports arbitrary feedforward topologies, like multilayer perceptrons and fully connected cascade networks
 CSuperNN::NeuronNeuron, that can contain connections to neurons in the next layers
 CSuperNN::RunnerAuxiliary class to ease the usage of an already trained neural network
 CSuperNN::SigmoidActivation functions were not implemented in an OO way due to performance
 CSuperNN::SigmoidSymmetricSigmoid symmetric function
 CSuperNN::SignSign function (net >= 0 ? 1 : -1)
 CSuperNN::SInfoMinimum / maximum scaling information
 CSuperNN::TrainingAlgorithmAbstract class that provides the calculation of the error derivatives and the error accumulation, used by the derived backpropagation training algorithms
 CSuperNN::ImplBackpropBase class for the standard backpropagation algorithm
 CSuperNN::BatchBatch backpropagation
 CSuperNN::IncrementalIncremental backpropagation
 CSuperNN::IRpropImproved resilient backpropagation algorithm
 CSuperNN::IRpropL1Modified improved resilient backpropagation algorithm
 CSuperNN::NBNNeuron by Neuron algorithm
 Cstd::vector< T >STL class
 CSuperNN::BoundsData scaling information, for all input and output neurons
 CSuperNN::DataData used in training, validation and testing
 CSuperNN::LayerArray of neurons