Overview | HNet | Performance Aspects | Mathematics | Biology
The brain employs an auto-correlative feature called neural plasticity.  This pertains to a process of "pruning" synaptic connections and related dendrites, as well as synaptic regrowth.  In this manner the brain is able to further adapt to its environment through “hardware” changes.  Within HNeT neural plasticity is also applied, whereby synapses and associated combinatorics are pruned through autocorrelation with the cortical memory element that receives the synaptic signal.

Cortical memory elements that display large magnitude indicate the input combinatoric is highly correlated to the response, and thus important in mapping out the stimulus-response environment to which they are exposed.  Low magnitudes indicate the correlation is low, and associated input synapses are less important.  Synaptic regrowth, triggered by lower magnitude, is performed given constraints assigned by the user (source cell, product order, spin).  The source cell identifies the axons from which input signals are read (i.e.  those cells whose outputs are used to generate the combinatoric).  Spin provides control over the application of complex conjugates in the generation of combinatorics.

The HNeT system provides the research scientist/application developer with a high level of control over learning and the associated features of neural plasticity.