Overview | HNet | Performance Aspects | Mathematics | Biology
 

The neuro-holographic process may divided into three principle components of operation; these being A) preprocess conversion, B) combinatorics and C) execution of the cortical cell in learning and recall.  Computational complexity is established by the numeric operations performed in each of these three stages.

Preprocess conversion applies methods such as mapping to phase through sigmoidal or histogram equalization functions; frequency domain conversions such as Fourier and Wavelet based transforms, and so on...  The remainder of the process consists of Complex Multiply (CM) operations in the combinatorial stage, Complex Multiply and ACcumulate operations (CMAC) within the cortical cell for learning and recall.  As such, computational load is determined primarily by the number of cortical memory elements and the average product order in combinatorics generation.

For instance, an HNeT assembly comprised of 1000 cortical memory elements and processing, on average, 2nd order combinatorics would require the processing resource shown to the left.  Computational overhead is linearly proportional to that required within a single neuron cell within traditional multi-cell, multi-layered ANS systems such as back-propagation (by a factor of 4).  Both rate of learning convergence and associative storage capacity for the neuro-holographic method dramatically exceeds that of conventional neural network architectures.