&lt;title&gt;Continuous logic equivalence models of Hamming neural network architectures with adaptive-correlated weighting&lt;/title&gt;

Krasilenko, Vladimir G.; Saletsky, Felix M.; Yatskovsky, Victor I.; Konaté, Karim

doi:10.1117/12.304973

Cited by 13 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Equivalence models of neural net autoassociative and heteroassociative memory (HАM) were offered in papers [5][6][7] . Simulation results of such equivalence models (EM) 8,9 have confirmed that the EM has such advantages as substantial increase of memory capacity and possibility to keep highly correlated patterns of considerable dimension. These researches of EM HAM have showed that these models allow to recognize vectors with 1024 components and considerable percent (to 25-30%) of damages, at the capacity of network which in 3 -4 times exceeds the amount of neurons 6,7,9 .…”

Section: Introductionsupporting

confidence: 58%

“…1, is defined by a cluster point, that it was the least distance. As a measure of closeness we used generalized normalized function equivalence ( nonequivalence ) 8 . Modification of MTNLEMs DAEW for spatio-invariant recognition of 2D images is considered in paper 17 .…”

Section: Modeling Combined With Self-learning Clustering Methods Of Immentioning

confidence: 99%

“…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 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Krasilenko¹,

Lazarev

Nikitovich³

2014

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

In the paper, we show that the nonlinear spatial non-linear equivalency functions on the basis of continuous logic equivalence (nonequivalence) operations have better discriminatory properties for comparing images. Further, using the equivalent model of multiport neural networks and associative memory, (including matrix-matrix and matrix-tensor with adaptive-weighted correlation, multi-port neural-net auto-associative and hetero-associative memory (MP NN AAM and HAM ) and the proposed architecture based on them, we show how we can modify these models and architectures for space-invariant associative recognition and clustering (high performance parallel clustering processing) images. We consider possible implementations of 2D image classifiers, devices for partitioning image fragments into clusters and their architectures. The main base unit of such architectures is a matrix-matrix or matrix-tensor equivalentor, which can be implemented on the basis of two traditional correlators. We show that the classifiers based on the equivalency paradigm and optoelectronic architectures with space-time integration and parallel-serial 2D images processing have advantages such as increased memory capacity (more than ten times of the number of neurons!), High performance in different modes . We present the results of associative significant dimension (128x128, 610x340) image recognitionrenewal modeling. It will be shown that these models are capable to recognize images with a significant percentage (20-30%) damaged pixels. The experimental results show that such models can be successfully used for auto-and heteroassociative pattern recognition. We show simulation results of using these modifications for clustering and learning models and algorithms for cluster analysis of specific images and divide them into categories of the array. Show example of a cluster division of image fragments, letters and graphics for clusters with simultaneous formation of the outputweighted spatial allocated images for each cluster. Show results of other of modeling experiments with images of large dimension, such as clustering fragments (blocks 7x 7, 3x3, 15x15 and other sizes), 610x340 elements images into 8 clusters. We show that it is the use of nonlinear processing and nonlinear functions improves the quality of classification and image recognition. We offer criteria for the quality evaluation of patterns clustering with such MP NN AAM. It is shown that time of learning in the proposed structures of multi-port neural net classifier / categorizer-clustering (MP NN C) on the basis of equivalency paradigm, due to their multi-port, decreases by orders and can be, in some cases, just a few epochs. Other experimental data is also shown.

show abstract

Section: Introductionsupporting

confidence: 58%

Section: Modeling Combined With Self-learning Clustering Methods Of Immentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Krasilenko¹,

Lazarev

Nikitovich³

2014

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…The strategic direction of solution of various scientific problems, including the problem of creation of artificial intelligence (AI) systems, human brain simulators, robotics systems, monitoring and control systems, decision-making systems, as well as systems based on artificial neural networks, etc, becomes fast-acting and parallel processing of large arrays (2-D) of data (up to 1024x1024 and higher) using non-conventional computational systems, corresponding matrix logics (multi-valued, signed-digit, fuzzy logics, continuous, neuro-fuzzy and others) and corresponding mathematical apparatus [1][2][3][4][5][6] . For numerous perspective realizations of optical learning neural networks (NN) with two dimensional structure 1 of recurrent optical NN 2 of the continuous logic equivalency models (CLEM) NN [3][4][5] , the elements of matrix logic are required, and not only of two-valued property, threshold, hybrid but also continuous, neuro-fuzzy logics and adequate structure of vector-matrix computational procedures with basic operations of abovementioned logics.…”

Section: Introductionmentioning

confidence: 99%

Smart time-pulse coding photoconverters as basic components 2D-array logic devices for advanced neural networks and optical computers

et al. 2004

Self Cite

View full text Add to dashboard Cite

The article deals with a conception of building arithmetic-logic devices (ALD) with a 2D-structure and optical 2D-array inputs-outputs as advanced high-productivity parallel basic operational training modules for realization of basic operation of continuous, neuro-fuzzy, multilevel, threshold and others logics and vector-matrix, vector-tensor procedures in neural networks, that consists in use of time-pulse coding (TPC) architecture and 2D-array smart optoelectronic pulse-width (or pulse-phase) modulators (PWM or PPM) for transformation of input pictures. The input grayscale image is transformed into a group of corresponding short optical pulses or time positions of optical two-level signal swing. We consider optoelectronic implementations of universal (quasi-universal) picture element of two-valued ALD, multi-valued ALD, analog-to-digital converters, multilevel threshold discriminators and we show that 2D-array time-pulse photoconverters are the base elements for these devices. We show simulation results of the time-pulse photoconverters as base components. Considered devices have technical parameters: input optical signals power is 200nW…200µW (if photodiode responsivity is 0.5A/W), conversion time is from tens of microseconds to a millisecond, supply voltage is 1.5…15V, consumption power is from tens of microwatts to a milliwatt, conversion nonlinearity is less than 1%. One cell consists of 2-3 photodiodes and about ten CMOS transistors. This simplicity of the cells allows to carry out their integration in arrays of 32×32, 64x64 elements and more.

show abstract

“…Besides, quality of recognition, in particular, the number of stored and correctly recognized references in neuroassociative memory, depends greatly on chosen matrix, type, space. In neuronetworks models and recognition algorithms in hidden layers, minimal spaces (while teaching) 2,10 and criteria of maximum convergency are used as intermediate criteria, in some new equivalence models for recognition of strongly corrected images 11,12 . The interest to these new directions, neurofuzzy models, logic-algebraic apparatus, common neurobionic principles can be explained by the possibility to understand with their help the principles of human brain functioning.…”

Section: Introductionmentioning

confidence: 99%

<title>Family of new operations equivalency of neuro-fuzzy logic: optoelectronic realization and applications</title>

Krasilenko¹,

Nikolsky

Yatskovsky

et al. 2002

Photonic and Quantum Technologies for Aerospace Applications IV

Self Cite

View full text Add to dashboard Cite

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.

show abstract

<title>Continuous logic equivalence models of Hamming neural network architectures with adaptive-correlated weighting</title>

Cited by 13 publications

References 7 publications

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

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

Smart time-pulse coding photoconverters as basic components 2D-array logic devices for advanced neural networks and optical computers

<title>Family of new operations equivalency of neuro-fuzzy logic: optoelectronic realization and applications</title>

Contact Info

Product

Resources

About