Package org.aika.neuron

Class Summary

Class	Description
Activation	The Activation class is the most central class in Aika.
Activation.Builder
Activation.Rounds	Since Aika is a recurrent neural network, it is necessary to compute several rounds of activation values.
Activation.State	A State object contains the activation value of an activation object that belongs to a neuron.
Activation.SynapseActivation	The SynapseActivation mirror the synapse link in the network of activations.
INeuron	The INeuron class represents a internal neuron implementation in Aikas neural network and is connected to other neurons through input synapses and output synapses.
INeuron.ThreadState	The ThreadState is a thread local data structure containing the activations of a single document for a specific logic node.
Neuron	The Neuron class is a proxy implementation for the real neuron implementation in the class INeuron.
Synapse	The Synapse class connects two neurons with each other.
Synapse.Builder	The Builder class is just a helper class which is used to initialize a neuron.
Synapse.Key

Enum Summary

Enum	Description
Activation.Mode
INeuron.Type