AbstractNeuron | Implementation helper for common types of Neurons |
ArgParser | |
CenterNeuron | A center-neuron, the building block of a Radial basis function network |
DynamicKohonenParameters | |
EucledianTopology | Standard eucledian topology OPT: zounds |
Exception | A common exception class used by all classes in the annie library |
ExKohonenDraw | |
File | The idea is that this class will be used to read in information from text files created by the "save" function in various annie classes |
GABNeuron | Neuron for Gain Adaptive BP |
HopfieldBase | A Hopfield network - content addressable memory and energy |
HopfieldBase::NData | |
HopfieldNetwork | A "standard" incarnation of the Hopfield network usable form most purposes |
Image | One image (actually a SDL_Context wrapper ..) |
Image::Color | Color components should be in [0, 1] |
ImageCompressor | (usually lossy) image compressor |
ImageCompressor::PartialListener | |
InputLayer | A layer of input neurons |
InputNeuron | Input neurons are slightly special |
KohonenAnalyzer | |
KohonenAnalyzer::Outs | |
KohonenDraw | Draws examples and progress of the Kohonen clustering using OpenGL --> Should be called from the redraw thread |
KohonenNetwork | Todo: getOutput (&& getWin*) doesn't give anything sensible in this impl |
KohonenNeuron | |
KohonenParameters | Note: it is closely tied to Topology - the meaning NeighborhoodSize depends on the Topology used |
Layer | Abstraction for a "layer" of neurons, i.e., a group of neurons not connected to each other |
Link | Abstraction of a connection between two neurons |
Matrix | A class for 2-dimensional matrices |
MLPCompressor | Yeah, yeah - ValueUpdateListener should have been inner class |
MLPKohonenAnalyzer | Analyzes MLP using Kohonen |
MultiLayerNetwork | Abstraction of a multi-layer perceptron network |
MultiLayerNetwork::Error | Error summator will be moved up for general use. |
Network | Another core class of the annie library, a generic template for a neural network |
Neuron | One of the fundamental annie classes - the basic Neuron |
NumberParameter | |
ParametrizedNeuron | Neuron with a parametrized activation function |
RadialBasisNetwork | A Radial Basis Function Neural Network |
RecurrentNetwork | RN constructed from a genotype |
RecurrentNeuron | A neuron used for recurrent networks |
Redrawer | |
RigidVisualiser | Simple text-mode visualiser, which prints updated value after each change (synchronous) |
Selector | Select features from the TS vectors |
Shrinker | |
Shuffler | Shuffles the given training set every nth epoch |
SimpleNeuron | A simple perceptron - i.e., it takes as input the weighted sum of the outputs of the neurons connected to it |
SimpleVisualiser | Simple text-mode visualiser, which prints updated value after each change (synchronous), it it didn't occur too soon |
StandardKohonenParameters | LearningParam = e ^ (- slope * ( ln (time) ^ 2 ) ) neighborHoodSize = (MAX_NB_SIZE) * learningParam |
StaticKohonenParameters | Static kohonen parameters - don't change unless changed by the user |
Stepper | Waits for keypress on each "epoch" if "stepped" is true |
StringParameter | Also holds the destination |
TerminatedException | |
TileCompressor | Compress image by dividing it to squares |
TLayer | Nice getters.. |
Topology | Class used as a template to the KohonenNetwork network |
TrainingSet | This is an abstraction for the set of patterns which are used to "train" a network |
TSTransformer | 2 vectors -> 2 vectors |
TwoLayerNetwork | Two layered networks are very commonly used |
Vector | |
Video | Video (and input) system maintaince |
Video::Redrawer | User redraw class. draw() will be called from the video thread |