

Evgeny Osipov
Professor
Luleå tekniska universitet
Luleå tekniska universitet
Datavetenskap
Institutionen för system- och rymdteknik
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
A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations (2023)
ACM Computing Surveys, Vol. 55, nr. 6
Artikel i tidskrift
A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges (2023)
ACM Computing Surveys, Vol. 55, nr. 9
Konferensbidrag
Evaluating Complex Sparse Representation of Hypervectors for Unsupervised Machine Learning (2022)
Ingår i: 2022 International Joint Conference on Neural Networks (IJCNN): 2022 Conference Proceedings, IEEE, 2022
Konferensbidrag
Few-shot Federated Learning in Randomized Neural Networks via Hyperdimensional Computing (2022)
Ingår i: 2022 International Joint Conference on Neural Networks (IJCNN), 2022 Conference Proceedings, IEEE, 2022
Artikel i tidskrift
Hyperseed: Unsupervised Learning With Vector Symbolic Architectures (2022)
IEEE Transactions on Neural Networks and Learning Systems