Overview | HNet | Performance Aspects | Mathematics | Biology
Neural plasticity refers to the operation of dynamically pruning cell processes (synaptic interconnections and related dendites) and regrowing new cell processes.  Neural plasticity within HNeT optimizes combinatoric selection of higher order input signals (Granule cell processing) through autocorrelation with cortical memory magnitude.
Application of neural plasticity dramatically improves the generalization capability of holographic neural assemblies.  The graph to the left illustrates typical error reduction when testing against independent validation data sets and applying neural plasticity.  This example illustrates the error reduction curve for an assembly trained to segment facial images from complex background clutter.

Five function interfaces are provided within the HNeT API for control of neural plasticity.  A broad range of options are provided, and different modes of pruning and regrowth are achieved by applying plasticity operations in various combination.