SuperNN
1.0.0
|
▼NSuperNN | |
CActFunc | Activation function dispatcher |
CBatch | Batch backpropagation |
CBounds | Data scaling information, for all input and output neurons |
CConnection | Synaptic connection between two neurons |
CData | Data used in training, validation and testing |
CElliot | Elliot sigmoid-like function |
CElliotSymmetric | Elliot sigmoid-like function (Symmetric) |
CException | The exception can be identified by the type() method |
CGaussian | Gaussian function |
CGaussianSymmetric | Gaussian symmetric function |
CImplBackprop | Base class for the standard backpropagation algorithm |
CIncremental | Incremental backpropagation |
CIRprop | Improved resilient backpropagation algorithm |
CIRpropL1 | Modified improved resilient backpropagation algorithm |
CLayer | Array of neurons |
CLinear | Linear function |
▼CNBN | Neuron by Neuron algorithm |
CHist | |
CNetwork | Artificial neural network structure that supports arbitrary feedforward topologies, like multilayer perceptrons and fully connected cascade networks |
CNeuron | Neuron, that can contain connections to neurons in the next layers |
CRunner | Auxiliary class to ease the usage of an already trained neural network |
CSigmoid | Activation functions were not implemented in an OO way due to performance |
CSigmoidSymmetric | Sigmoid symmetric function |
CSign | Sign function (net >= 0 ? 1 : -1) |
CSInfo | Minimum / maximum scaling information |
CTrainingAlgorithm | Abstract class that provides the calculation of the error derivatives and the error accumulation, used by the derived backpropagation training algorithms |