Main Page | Namespace List | Class Hierarchy | Alphabetical List | Class List | File List | Namespace Members | Class Members | File Members | Related Pages

Annie Class List

Here are the classes, structs, unions and interfaces with brief descriptions:
AbstractNeuronImplementation helper for common types of Neurons
CenterNeuronA center-neuron, the building block of a Radial basis function network
EucledianTopologyStandard eucledian topology OPT: zounds
ExceptionA common exception class used by all classes in the annie library
FileThe idea is that this class will be used to read in information from text files created by the "save" function in various annie classes
GABNeuronNeuron for Gain Adaptive BP
HopfieldBaseA Hopfield network - content addressable memory and energy
HopfieldNetworkA "standard" incarnation of the Hopfield network usable form most purposes
ImageOne image (actually a SDL_Context wrapper ..)
Image::ColorColor components should be in [0, 1]
ImageCompressor(usually lossy) image compressor
InputLayerA layer of input neurons
InputNeuronInput neurons are slightly special
KohonenDrawDraws examples and progress of the Kohonen clustering using OpenGL --> Should be called from the redraw thread
KohonenNetworkTodo: getOutput (&& getWin*) doesn't give anything sensible in this impl
KohonenParametersNote: it is closely tied to Topology - the meaning NeighborhoodSize depends on the Topology used
LayerAbstraction for a "layer" of neurons, i.e., a group of neurons not connected to each other
LinkAbstraction of a connection between two neurons
MatrixA class for 2-dimensional matrices
MLPCompressorYeah, yeah - ValueUpdateListener should have been inner class
MLPKohonenAnalyzerAnalyzes MLP using Kohonen
MultiLayerNetworkAbstraction of a multi-layer perceptron network
MultiLayerNetwork::ErrorError summator will be moved up for general use.
NetworkAnother core class of the annie library, a generic template for a neural network
NeuronOne of the fundamental annie classes - the basic Neuron
ParametrizedNeuronNeuron with a parametrized activation function
RadialBasisNetworkA Radial Basis Function Neural Network
RecurrentNetworkRN constructed from a genotype
RecurrentNeuronA neuron used for recurrent networks
RigidVisualiserSimple text-mode visualiser, which prints updated value after each change (synchronous)
SelectorSelect features from the TS vectors
ShufflerShuffles the given training set every nth epoch
SimpleNeuronA simple perceptron - i.e., it takes as input the weighted sum of the outputs of the neurons connected to it
SimpleVisualiserSimple text-mode visualiser, which prints updated value after each change (synchronous), it it didn't occur too soon
StandardKohonenParametersLearningParam = e ^ (- slope * ( ln (time) ^ 2 ) ) neighborHoodSize = (MAX_NB_SIZE) * learningParam
StaticKohonenParametersStatic kohonen parameters - don't change unless changed by the user
StepperWaits for keypress on each "epoch" if "stepped" is true
StringParameterAlso holds the destination
TileCompressorCompress image by dividing it to squares
TLayerNice getters..
TopologyClass used as a template to the KohonenNetwork network
TrainingSetThis is an abstraction for the set of patterns which are used to "train" a network
TSTransformer2 vectors -> 2 vectors
TwoLayerNetworkTwo layered networks are very commonly used
VideoVideo (and input) system maintaince
Video::RedrawerUser redraw class. draw() will be called from the video thread

Generated on Fri Jun 18 13:18:49 2004 for Annie by doxygen 1.3.5