The continuous logic "equivalental" models (CLEM) of Hamming neural networks (NN) with adaptive-correlated weighting (HNN ACW) and multiport associative memory (MAM) based on equivalence operation of neural logic are considered. The models for simple network with weighted correlation coefficient, for network with adapted weighting and double weighting and their system equivalental func ions are suggested. The models require calculations based on two-step algorithms and vector-matrix procedures with the normalized equivalence operation. Modified equivalence models of neural networks and associative memory for space-invariant 2D pattern recognition are proposed. Possible variants of the models implementation are considered. Neural networks architecture for invariant 2D pettern recognition consist of equivalentors, every of which replace two correlators.

The perspective of neural networks equivalental models (EM) base on vector-matrix procedure with basic operations of continuous and neuro-fuzzy logic (equivalence, absolute difference) are shown. Capacity on base EMs exceeded the amount of neurons in 2,5 times. This is larger than others neural networks paradigms. Amount neurons of this neural networks on base EMs may be 10 -20 thousands. The base operations in EMs are normalized equivalency operations. The family of new operations "equivalency" and "non-equivalency" of neuro-fuzzy logic's, which we have elaborated on the based of such generalized operations of fuzzy-logic's as fuzzy negation, t-norm and s-norm are shown. Generalized rules of construction of new functions (operations) "equivalency" which uses relations of t-norm and snorm to fuzzy negation are proposed. Among these elements the following should be underlined: 1) the element which fulfills the operation of limited difference; 2) the element which algebraic product (intensifier with controlled coefficient of transmission or multiplier of analog signals); 3) the element which fulfills a sample summarizing (uniting) of signals (including the one during normalizing). Synthesized structures which realize on the basic of these elements the whole spectrum of required operations: t-norm, s-norm and new operations -"equivalency" are shown. These realization on the basic of new multifunctional optoelectronical BISPIN-devices (MOEBD) represent the circuit with constant and pulse optical input signals. They are modeling the operation of limited difference. These circuits realize frequency-dynamic neuron models and neural networks. Experimental results of these MOEBD and "equivalency" circuits, which fulfil the limited difference operation are discussed. For effective realization of neural networks on the basic of EMs as it is shown in report, picture elements are required as main nodes to implement element operations "equivalence" ("non-equivalence") of neuro-fuzzy logic's.

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.