|
 |
| Mikhail Kiselev |
|---|
| Megaputer Intelligence, Cheboxary |
| Regular Member |
| Personal Web Site: |
| Main page: http://www.mirlabs.net/global/index.php?c=main&a=person&id=666 |
| Short Biography |
| I was born in 1966 in Moscow. I studied in Moscow State University Department of Theoretical Physics (including post-graduate course) in 1983-1992. In 1993 I obtained Ph.D. degree in Moscow Baumann University of Technology Biocybernetics Department. Theme of my Ph.D. thesis was use of artificial intelligence methods in surgical intraopertaional monitoring system. In 1994 I (together with Dr. S. Arseniev) founded Megaputer Intelligence company and began to develop its main product, data mining system PolyAnalyst. In late 90 I developed methods for evolutionary programming and, on their base, the module of automated non-linear regression was implemented in PolyAnalyst. Later my scientific interests included natural language processing and analysis (automated fact extraction, semantic maps and so on). Since early 00s I carry out research in spiking neural network theory. In the beginning it was devoted to patter recognition methods. At present, topic of my research is simulation of short-term memory in SNNs and polychronization effects in them. |
| List of top 5 publications in the last 5 years |
1. Kiselev M. V.: Self-organized Short-Term Memory Mechanism in Spiking Neural Network, Proceedings of ICANNGA 2011 Part I, Ljubljana, pp 120-129. 2. Kiselev, M. V.: Formation of short-term memory in spiking neural networks, Proceedings of Neuroinformatics-2011, Moscow, vol 1, pp 269-278. 3. Kiselev, M. V.: Self-organized Spiking Neural Network Recognizing Phase/Frequency Correlations, Proceedings of IJCNN’2009, Atlanta, Georgia, pp 1633-1639. 4. Kiselev, M. V.: One layer self-organized spiking neural network recognizing synchrony structure in input signal, «Neurocomputer», №10, 2009, pp 3-11. 5. Kiselev, M. V.: Text Clustering Procedure Based on Pair-wise Proximity of Key Terms and its Comparison with Metric Clustering Methods, «Internet-mathematics 2007», Moscow, Yandex publishing, 2007, pp. 74-83. |
| List of top 5 academic activities during the last 5 years |