Hoppa till innehållet
Evgeny Osipov
Evgeny Osipov

Evgeny Osipov

Professor
Luleå tekniska universitet
Datavetenskap
Institutionen för system- och rymdteknik
evgeny.osipov@ltu.se
0920-491578
A3313 Luleå

General Information

Dr. Evgeny Osipov is a full professor in Dependable Communication and Computation Systems. 

Research Interests

His main research interests are within Artificial Intelligence. His area of expertise is Vector Symbolic Architectures, also known as  hyperdimensional computing. VSA is a computing framework for explaining  and expressing AI functionality from the standpoints of mathematical properties of random hyperdimensional spaces. It serves as a bridge between the symbolic and connectionist AI approaches and is prospected as one of the main candidates for creating artificial general intelligence.  

Education

  • (2005) PhD in Computer Science (predicate “Cum Laude”). University of Basel, Department of Computer Science, Basel, Switzerland.
  • (2003) Licentiate of Technology in Telecommunications. KTH, Royal Institute of Technology, Department of Microelectronics and Information Technology, Stockholm, Sweden.
  • (1999) Pre-doctoral school in Communication Systems. EPFL, Swiss Federal Institute of Technology,  Pre-doctoral school, Lausanne, Switzerland.
  • (1998) Engineer (degree with Honors). KGTU, Krasnoyarsk StateTechnical University, Faculty of Computer Science, Krasnoyarsk, Russia.

Publikationer

Artikel i tidskrift

Integer Echo State Networks: Efficient Reservoir Computing for Digital Hardware (2022)

Kleyko. D, Frady. E, Kheffache. M, Osipov. E
IEEE Transactions on Neural Networks and Learning Systems, Vol. 33, nr. 4, s. 1688-1701
Artikel i tidskrift

Vector Semiotic Model for Visual Question Answering (2022)

Kovalev. A, Shaban. M, Osipov. E, Panov. A
Cognitive Systems Research, Vol. 71, s. 52-63
Konferensbidrag

Compressed Superposition of Neural Networks for Deep Learning in Edge Computing (2021)

Zeman. M, Osipov. E, Bosnić. Z
Ingår i: 2021 International Joint Conference on Neural Networks (IJCNN) Proceedings, IEEE, 2021
Artikel i tidskrift

Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks (2021)

Kleyko. D, Kheffache. M, Frady. E, Wiklund. U, Osipov. E
IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, nr. 8, s. 3777-3783
Konferensbidrag

HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing Enabled Embedding of n-gram Statistics (2021)

Alonso. P, Shridhar. K, Kleyko. D, Osipov. E, Liwicki. M
Ingår i: 2021 International Joint Conference on Neural Networks (IJCNN) Proceedings, IEEE, 2021