Igor Aizenberg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Igor Aizenberg has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Jaakko Astola
Department of Signal Processing, Tampere University of Technology, Finland
2 shared publications - Antonio Luchetta
Department of Information Engineering, Università degli Studi di Firenze, Via di Santa Marta 3, 50139 Firenze, Italy
1 shared publication - Claudio Moraga
European Centre for Soft Computing
1 shared publication - Claudio Moraga
Technical University of Dortmund
1 shared publication D. Paliy
1 shared publication- Dmitriy Paliy
Institute of Signal Processing, Tampere University of Technology, P.O. Box 553, 33101 Tampere, Finland
1 shared publication
Latest Publications
- 14 July 2012
- Published by Springer Nature in Soft Computing
- Vol. 17 (2) , 265-273
Hebbian and error-correction learning for complex-valued neurons
- 14 July 2012
- Published by Springer Nature in Soft Computing
- Vol. 17 (2) , 265-273
Hebbian and error-correction learning for complex-valued neurons
- 21 August 2011
- Published by Springer Nature in Soft Computing
- Vol. 16 (4) , 563-575
A modified learning algorithm for the multilayer neural network with multi-valued neurons based on the complex QR decomposition
- 21 August 2011
- Published by Springer Nature in Soft Computing
- Vol. 16 (4) , 563-575
A modified learning algorithm for the multilayer neural network with multi-valued neurons based on the complex QR decomposition
- 1 January 2011
- Published by Springer Nature
- p. 223-235
On the Projection of k-Valued Non-linearly Separable Problems into m-Valued Linearly Separable Problems
- 1 January 2011
- Published by Springer Nature
- p. 223-235
On the Projection of k-Valued Non-linearly Separable Problems into m-Valued Linearly Separable Problems
- 1 January 2011
- Published by Springer Nature
- p. 207-248
Applications of MVN and MLMVN
- 1 January 2011
- Published by Springer Nature
- p. 173-206
Multi-Valued Neuron with a Periodic Activation Function
- 1 January 2011
- Published by Springer Nature
- p. 173-206
Multi-Valued Neuron with a Periodic Activation Function
- 1 January 2011
- Published by Springer Nature
- p. 133-172
Multilayer Feedforward Neural Network Based on Multi-Valued Neurons (MLMVN)
- 1 January 2011
- Published by Springer Nature
- p. 133-172
Multilayer Feedforward Neural Network Based on Multi-Valued Neurons (MLMVN)
- 1 January 2011
- Published by Springer Nature
- p. 95-132
MVN Learning
- 1 November 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 21 (12) , 1939-1949
Periodic Activation Function and a Modified Learning Algorithm for the Multivalued Neuron
In this paper, we consider a new periodic activation function for the multivalued neuron (MVN). The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN outperforms many other neurons and MVN-based neural networks have shown their high potential, the MVN still has a limited capability of learning highly nonlinear functions. A periodic activation function, which is introduced in this paper, makes it possible to learn nonlinearly separable problems and non-threshold multiple-valued functions using a single multivalued neuron. We call this neuron a multivalued neuron with a periodic activation function (MVN-P). The MVN-Ps functionality is much higher than that of the regular MVN. The MVN-P is more efficient in solving various classification problems. A learning algorithm based on the error-correction rule for the MVN-P is also presented. It is shown that a single MVN-P can easily learn and solve those benchmark classification problems that were considered unsolvable using a single neuron. It is also shown that a universal binary neuron, which can learn nonlinearly separable Boolean functions, and a regular MVN are particular cases of the MVN-P.
- 1 November 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 21 (12) , 1939-1949
Periodic Activation Function and a Modified Learning Algorithm for the Multivalued Neuron
In this paper, we consider a new periodic activation function for the multivalued neuron (MVN). The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN outperforms many other neurons and MVN-based neural networks have shown their high potential, the MVN still has a limited capability of learning highly nonlinear functions. A periodic activation function, which is introduced in this paper, makes it possible to learn nonlinearly separable problems and non-threshold multiple-valued functions using a single multivalued neuron. We call this neuron a multivalued neuron with a periodic activation function (MVN-P). The MVN-Ps functionality is much higher than that of the regular MVN. The MVN-P is more efficient in solving various classification problems. A learning algorithm based on the error-correction rule for the MVN-P is also presented. It is shown that a single MVN-P can easily learn and solve those benchmark classification problems that were considered unsolvable using a single neuron. It is also shown that a universal binary neuron, which can learn nonlinearly separable Boolean functions, and a regular MVN are particular cases of the MVN-P.