Formation of similarity-reflecting binary vectors with random binary projections

DA Rachkovskij - Cybernetics and Systems Analysis, 2015‏ - Springer
We propose a transformation of real input vectors to output binary vectors by projection
using a binary random matrix with elements {0, 1} and thresholding. We investigate the rate …

Feedback associative memory based on a new hybrid model of generalized regression and self-feedback neural networks

M Amiri, H Davande, A Sadeghian, S Chartier - Neural networks, 2010‏ - Elsevier
The focus of this paper is to propose a hybrid neural network model for associative recall of
analog and digital patterns. This hybrid model consists of self-feedback neural network …

Estimation of vectors similarity by their randomized binary projections

DA Rachkovskij - Cybernetics and Systems Analysis, 2015‏ - Springer
We analyze the estimation of the angle, scalar product, and the Euclidean distance of real-
valued vectors using binary vectors with controlled sparsity. Transformation is carried out by …

Model selection criteria for a linear model to solve discrete ill-posed problems on the basis of singular decomposition and random projection

EG Revunova - Cybernetics and Systems Analysis, 2016‏ - Springer
Criteria are developed to determine the optimal number of components of a linear model in
solving a discrete ill-posed problem by the methods of truncated singular value …

Analytical study of error components for solving discrete ill-posed problems using random projections

EG Revunova - Cybernetics and Systems Analysis, 2015‏ - Springer
This article analytically studies the dependence of components of the error of reconstructing
the true signal on the number of rows of a random projection matrix. It is shown that, with …

Applied artificial neural networks: From associative memories to biomedical applications

M Amiri, K Derakhshandeh - Edited by Kenji Suzuki, 2011‏ - books.google.com
Due to remarkable capabilities of artificial neural networks (ANNs) such as generalization
and nonlinear system modeling, ANNs have been extensively studied and applied in a wide …

Ідентифікація та автоматизоване керування в умовах процесів збагачувальної технології на основі методів обчислювального інтелекту

АІ Купін, АИ Купин, АО Сенько, БС Мисько - 2018‏ - ds.knu.edu.ua
Друге видання монографії, перероблене та доповнене. Досліджено питання здійснення
ідентифікації із застосуванням нейромережевих підходів у складі інтелектуальних …

Analysis of the dynamical behavior of a feedback auto-associative memory

M Amiri, S Saeb, MJ Yazdanpanah, SA Seyyedsalehi - Neurocomputing, 2008‏ - Elsevier
The dynamical behavior and the stability properties of fixed points in a feedback auto-
associative memory are investigated. The proposed structure encompasses a multi-layer …

[HTML][HTML] ANN-Based Discernment of Septic and Inflammatory Synovial Fluid: A Novel Method Using Viscosity Data from a QCR Sensor

A Miranda-Martínez, B Sufrate-Vergara… - Sensors, 2022‏ - mdpi.com
The synovial fluid (SF) analysis involves a series of chemical and physical studies that allow
opportune diagnosing of septic, inflammatory, non-inflammatory, and other pathologies in …

Auto-associative memory based on a new hybrid model of SFNN and GRNN: performance comparison with NDRAM, ART2 and MLP

H Davande, M Amiri, A Sadeghian… - 2008 IEEE International …, 2008‏ - ieeexplore.ieee.org
Currently, associative neural networks (AsNNs) are among the most extensively studied and
understood neural paradigms. In this paper, we use a hybrid model of neural network for …