Denis Kleyko

Assistant Professor

AASS Research Center
School of Science and Technology
Örebro University
70182 Örebro, Sweden
Room: T2227
Phone: No Phone Number Available
Email: denis.kleyko@oru.se

Google Scholar

Denis Kleyko is an Assistant Professor in Computer Science at Örebro University. Denis obtained his Ph.D. in Computer Science in 2018 from Luleå University of Technology. Prior to joining Örebro University, he has completed three postdoctoral stays at different instritutions. The first stay was at the Department of Computer Science, Electrical and Space Engineering at Luleå University of Technology (2018-2019), the second one was at the Redwood Center for Theoretical Neuroscience at University of California at Berkeley (2020-2022), and the third one was at Intelligent Systems Lab at Research Institutes of Sweden (2022-2023). The last two stays were a part of the Marie Skłodowska-Curie Global Individual Fellowship that Denis was awarded in 2019.

Denis’s fascination for research is in computing with randomness that manifistates in how complex can be the functionality of seemingly simple algorithms that rely on some form of randomness. In particular, he is interested in how could randomness benefit algorithms within artificial intelligence and machine learning. One of his primary interests is a computing framework of vector symbolic architectures, which is also known as hyperdimensional computing, which exploits randomness for knowledge representation, computing, learning, and reasoning. He seeks to understant how this framework could be connected to emerging low-power computing hardware and how could it enable the design of novel architectures for artificial neural networks. Broadly, his research interests also include numerous information processing methods both brain- and physics-inspired such as reservoir computing, associative memories, prototype-based learning, cellular automata computations, sparse coding, kernel-based methods, Ising machines, sketching techniques, self-organizing maps, and formation of similarity-preserving embeddigns.

As a part of community service, Denis is a webmaster and an author of a website dedicated to hyperdimensional computing – www.hd-computing.com . He also helps organizing regular series of webinars on this topic – “ Online Speakers’ Corner on Vector Symbolic Architectures and Hyperdimensional Computing ”.

Denis is an IEEE Senior Member , a Member of the European Laboratory for Learning and Intelligent Systems (ELLIS Society), and a Member of the Marie Curie Alumni Association .


Publications

[1] K. Schlegel, D. Kleyko, B. H. Brinkmann, E. S. Nurse, R. W. Gayler and P. Neubert. Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals. Nature Machine Intelligence, pages 1-2, 2024BibTeX | DiVA ]
[2] C. J. Kymn, D. Kleyko, E. P. Frady, C. Bybee, P. Kanerva, F. T. Sommer and B. A. Olshausen. Computing with Residue Numbers in High-Dimensional Representation. 2023BibTeX | DiVA ]