Activation class is the most central class in Aika.SynapseActivation mirror the synapse link in the network of activations.State object contains the activation value of an activation object that belongs to a neuron.StateChange class is used to store the state change of an activation that occurs in each node of
the binary search tree.InputNode and the AndNode classes together form a pattern lattice, containing all
possible substructures of any given conjunction.node is an interesting pattern that might be considered for further processing.Document class represents a single document which may be either used for processing a text or as
training input.getFinalActivations is a convenience method to retrieve all activations of the given neuron that
are part of the final interpretation.INeuron class represents a internal neuron implementation in Aikas neural network and is connected to other neurons through
input synapses and output synapses.ThreadState is a thread local data structure containing the activationsBySlotAndPosition of a single document for
a specific logic node.InputNode class is the input layer for the boolean logic.Linker class is responsible for for the linkage of neuron activations.Neuron class is a proxy implementation for the real neuron implementation in the class INeuron.Node class is the abstract class for all the boolean logic nodes underneath the neural network layer.ThreadState is a thread local data structure containing the activations of a single document for
a specific logic node.process needs to be called after all the input activations have been added to the
network.in.SearchNode class represents a node in the binary search tree that is used to find the optimal
interpretation for a given document.recurrent specifies if input is a recurrent feedback link.Synapse class connects two neurons with each other.Builder class is just a helper class which is used to initialize a neuron.out.Copyright © 2018. All rights reserved.