Package NearNeural

Interface Summary

Interface	Description
BackPropagationMethod	Allows formally-specified backpropagation methods to be defined in order to modify the training of the net.
Neuron	Neurons are the staple of the net.
ThresholdingAlgorithm	A formal definition of an algorithm which adjusts input values.

Class Summary

Class	Description
Edge	This represents an edge in a NearNeural net.
HyperbolicTangentThresholdModel	Creates a new thresholding algorithm based on the hyperbolic tangent function.
LinearThresholdModel	A threshold which is linear.This method may not work at all with some backpropagation methods
NeuralNet	A practical implementation of a feed-forward back propogating multi-layer perceptron network.
NeuronLayer	A NeuronLayer keeps track of an arbitrary selection of neurons, each of which may have arbitrary or even circular links.
ReceptiveNeuron	A receptive Neuron is a form of Neuron that maintains Edges, which themselves point to other Neurons, be they static or themselves a form of Receptive Neuron.
ReceptiveNeuronLayer	A Receptive form of the Neuron Layer, this class allows Neurons to maintain Edges to other Neurons.
SigmoidThresholdModel	Represents a thresholding algorithm based on the sigmoid function.
SinusoidalThresholdModel	Creates a new sinusoidal thresholding algorithm.
StaticNeuron	Represents an input neuron, which has a static value, uninfluenced by any edges.
StaticNeuronLayer	The Static Neuron Layer holds only Static neurons, that is those without any Edges.
ThreadedUnweightedBackPropagationMethod	A threaded version of UnweightedBackPropagationMethod which uses a standard gradient-descent backpropagation method.
ThreePointRuleDifferentiation	Implements a numerical method for differentiation.
UnweightedBackPropagationMethod	Backpropagates a layer without any kind of weighting to avoid local minima of error.
WeightedThresholdModel	This class contains the necessary code to implement coefficient management in order to adjust a thresholding function.

Exception Summary

Exception	Description
IndexOutOfBoundsException	Represents an exception caused by attempting to address an absent Neuron or other Net element.
ItemNotFoundException	Represents an exception caused by attempting to access an absent Neuron or other Net element.
NeuralNetException	A throwable exception that is the parent of all other exceptions regarding nets.
UnresolvedValueException	An exception that handles values which are not processable as to the user's requests.
ValueOutOfBoundsException	An exception that is generally thrown when a value is out of acceptable bounds.