The concept models and implementations of multiport neural net associative memory for 2D patterns

Abstract

The paper considers neural net models and training and recognizing algorithms with base neurobiologic operations: p-step autoequivalence and non-equivalenc The Modified equivalently models (MEMs) of multiport neural net associative memory (MNNAM) are offered with double adaptive -equivalently weighing (DAEW) for recognition of 2D-patterns (images). It is shown, the computing process in MNNAM under using the proposed MEMs, is reduced to two-step and multi-step algorithms and step-by-step matrix-matrix (tensor-tensor) procedures. The given results of computer simulations confirmed the perspective of such models. Besides the result was received when MNNAM capacity on base of MEMs exceeded the amount of neurons.

Experimental research of methods for clustering and selecting image fragments using spatial invariant equivalent models

“…These signals are actually coefficients β in appropriate models described in Section 2.1. If the models use only weighing by this coefficient β of appropriate weighting matrix or tensor synapse connections, as it has been shown in papers 5,10,12,16 , increasing the k-order of nonlinear transformations are necessary for improving adaptation and increasing the quality of the similarity measure determination of images. If the models use the additional weighing of matrices or tensors connections array of coefficients α (vector for vector or matrix for 2D input data) according to formula (1), in architecture, as seen in Fig.…”

“…This can be achieved only with corresponding architectures based on optical and optoelectronic realization with spatial and time integration 10,12 . In paper 16 it was shown that the optoelectronic architecture with time integration can provide significant benefits and performance 10 9 -10 10 connections per second and they can be used to realize and multiport autoassociative and multiport heteroassociative memory (MNNAAM and MNNHAM).…”

“…The rule of learning consists in forming of matrix TXY (for simplicity in formulas designated simply T) of weight coefficients of synapsis connections for different models (І, ІІ, ІІІ), presented in paper 10 and described below for general case (III -model with double weighing) by formula (1):…”

“…In papers 10-12 on the basic idea from paper 5 multiport neural networks models of autoassociative memory (MАM) and multiport heteroassociative memory (MHAM) for associative storage and recognition of optical images are proposed and simulated. Mathematical models and principles and implement of autoassociative memory (AM) based on EM initiated in paper 5 , and described in detail in papers 6,10 and their modification -in paper 12 .…”

“…This previous clustering allows organizing proper automated grouping processed data, to cluster analysis, to evaluate on the basis of many signs each cluster, put a class label and improve subsequent learning procedures and classification in intelligent systems. At the same time, knowing the significant advantages of equivalence models (EM) when creating on their basis improved neural network recognition systems [7][8][9][10][11][12] and multiport autoassociative and heteroassociative memory [10][11][12] , there was a suggestion about the possibility of modifying EM and MHAM for parallel cluster image analysis [13][14] . Hardware implementations of these models are based on optoelectronic structures, including matrix-tensor multipliers, equivalentors and correlators with spatial and tine integration 15,16 .…”