Alexander Goltsev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alexander Goltsev has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Volodymyr I. Gritsenko
International Research and Training Center for Information Technologies and Systems of National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Kyiv, Ukraine
5 shared publications A Frolov
Institute for Theoretical Physics, University of Linz, Austria
1 shared publicationA Kartashov
Institute for Theoretical Physics, University of Linz, Austria
1 shared publication- Dmitri A. Rachkovskij
Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 971 87 Luleå, Sweden
1 shared publication Donald C. Wunsch
Cybernetics Centre of Ukrainian Academy of Sciences, Pr. Glushkova 40, Kiev, 252650 GSP Ukraine
1 shared publication- Donald C. Wunsch
Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA
1 shared publication
Latest Publications
- 1 October 2025
- Published by Springer Nature
- p. 269-283
A Perceptron-Like Neural Network Implementing a Learning-Capable K-Nearest Neighbor Classifier
- 1 October 2025
- Published by Springer Nature
- p. 269-283
A Perceptron-Like Neural Network Implementing a Learning-Capable K-Nearest Neighbor Classifier
- Open Access
- 28 April 2022
- Published by Universitat Autonoma de Barcelona in ELCVIA Electronic Letters on Computer Vision and Image Analysis
- Vol. 21 (1) , 102-110
A neural network with competitive layers for character recognition
A structure and functioning mechanisms of a neural network with competitive layers are described. The network is intended to solve the character recognition task. The network consists of several competitive layers of neurons. Each layer is a neural network consisting of a number of neurons represented as a layer. The number of neural layers is equal to the number of recognized classes. All neural layers have one-to-one correspondence with one another and with the input raster. The neurons of every layer have mutual lateral learning connections, which weights are modified during the learning process. There is a competitive (inhibitory) relationship between all neural layers. This competitive interaction is realized by means of a “winner-take-all” (WTA) procedure which aim is to select the layer with the highest level of neural activity.Validation of the network has been done in experiments on recognition of handwritten digits of the MNIST database. The experiments have demonstrated that its error rate is few less than 2%, which is not a high result, but it is compensated by rather fast data processing and a very simple structure and functioning mechanisms.
- 28 April 2022
- Published by Universitat Autonoma de Barcelona in ELCVIA Electronic Letters on Computer Vision and Image Analysis
- Vol. 21 (1) , 102-110
Open AccessA neural network with competitive layers for character recognition
A structure and functioning mechanisms of a neural network with competitive layers are described. The network is intended to solve the character recognition task. The network consists of several competitive layers of neurons. Each layer is a neural network consisting of a number of neurons represented as a layer. The number of neural layers is equal to the number of recognized classes. All neural layers have one-to-one correspondence with one another and with the input raster. The neurons of every layer have mutual lateral learning connections, which weights are modified during the learning process. There is a competitive (inhibitory) relationship between all neural layers. This competitive interaction is realized by means of a “winner-take-all” (WTA) procedure which aim is to select the layer with the highest level of neural activity.Validation of the network has been done in experiments on recognition of handwritten digits of the MNIST database. The experiments have demonstrated that its error rate is few less than 2%, which is not a high result, but it is compensated by rather fast data processing and a very simple structure and functioning mechanisms.
- 1 January 2017
- Published by Czech Technical University in Prague - Central Library in Neural Network World
- Vol. 27 (5) , 447-477
EXTRACTION OF HOMOGENEOUS FINE-GRAINED TEXTURE SEGMENTS IN VISUAL IMAGES
- 1 January 2017
- Published by Czech Technical University in Prague - Central Library in Neural Network World
- Vol. 27 (5) , 447-477
EXTRACTION OF HOMOGENEOUS FINE-GRAINED TEXTURE SEGMENTS IN VISUAL IMAGES
- 1 July 2015
- Published by Elsevier in Biologically Inspired Cognitive Architectures
- Vol. 13, 63-74
Modular neural networks with radial neural columnar architecture
- 1 July 2015
- Published by Elsevier in Biologically Inspired Cognitive Architectures
- Vol. 13, 63-74
Modular neural networks with radial neural columnar architecture
- 6 June 2015
- Published by Springer Nature
- p. 287-300
Finding the Texture Features Characterizing the Most Homogeneous Texture Segment in the Image
- 6 June 2015
- Published by Springer Nature
- p. 287-300
Finding the Texture Features Characterizing the Most Homogeneous Texture Segment in the Image
- 1 April 2012
- Published by Elsevier in Neural Networks
- Vol. 28, 15-23
Investigation of efficient features for image recognition by neural networks
- 1 April 2012
- Published by Elsevier in Neural Networks
- Vol. 28, 15-23
Investigation of efficient features for image recognition by neural networks
- 1 June 2009
- Published by Elsevier in Neurocomputing
- Vol. 72 (10-12) , 2477-2482
Modular neural networks with Hebbian learning rule
- 1 June 2009
- Published by Elsevier in Neurocomputing
- Vol. 72 (10-12) , 2477-2482
Modular neural networks with Hebbian learning rule
- 1 March 2005
- Published by Elsevier in Pattern Recognition
- Vol. 38 (3) , 315-322
Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings
- 1 March 2005
- Published by Elsevier in Pattern Recognition
- Vol. 38 (3) , 315-322
Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings
- 1 December 2004
- Published by Elsevier in Neurocomputing
- Vol. 62, 405-426
Secondary learning in the assembly neural network
- 1 December 2004
- Published by Elsevier in Neurocomputing
- Vol. 62, 405-426
Secondary learning in the assembly neural network
- 1 December 2004
- Published by Elsevier in Neurocomputing
- Vol. 62, 405-426
Secondary learning in the assembly neural network
- 1 December 2004
- Published by Elsevier in Neurocomputing
- Vol. 62, 405-426
Secondary learning in the assembly neural network