Denis Kleyko

Assistant Professor

AASS Research Center
School of Science and Technology
Örebro University
70182 Örebro, Sweden
Room: No Room Available
Phone: No Phone Number Available
Email: No Email Address Available

Google Scholar

Publications

[1] 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. Neural Computation, 37(1):1-37, 2025 [ BibTeX | DiVA ]
[2] D. Kleyko, C. J. Kymn, A. Thomas, B. A. Olshausen, F. T. Sommer and E. P. Frady. Principled neuromorphic reservoir computing. Nature Communications, 16(1), 2025 [ BibTeX | DiVA ]
[3] C. J. Kymn, S. Mazelet, A. Thomas, D. Kleyko, E. P. Frady, F. T. Sommer and B. A. Olshausen. Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps. 2024 [ BibTeX | DiVA ]
[4] C. J. Kymn, S. Mazelet, A. Thomas, D. Kleyko, E. P. Frady, F. T. Sommer and B. A. Olshausen. Binding in Hippocampal-entorhinal Circuits Enables Compositionality in Cognitive Maps. In Advances in Neural Information Processing Systems 38 (NeurIPS 2024) : Proceedings of the international conference Neural Information Processing Systems 2024, 38(38), 2024 [ BibTeX | DiVA ]
[5] C. J. Kymn, S. Mazelet, A. Ng, D. Kleyko and B. A. Olshausen. Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks. In 2024 Neuro Inspired Computational Elements Conference (NICE) 2024 [ BibTeX | DiVA ]
[6] E. Osipov, S. Kahawala, D. Haputhanthri, T. Kempitiya, D. De Silva, D. Alahakoon and D. Kleyko. Hyperseed : Unsupervised learning with vector symbolic architectures. IEEE Transactions on Neural Networks and Learning Systems, 35(5):6583-6597, 2024 [ BibTeX | DiVA ]
[7] 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, 6(2):243-244, 2024 [ BibTeX | DiVA ]
[8] D. Kleyko and D. A. Rachkovskij. On Design Choices in Similarity-Preserving Sparse Randomized Embeddings. In 2024 International Joint Conference on Neural Networks (IJCNN) 2024 [ BibTeX | DiVA ]
[9] D. Kleyko, A. Rosato, E. Paxon Frady, M. Panella and F. T. Sommer. Perceptron Theory Can Predict the Accuracy of Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 35(7):9885-9899, 2024 [ BibTeX | DiVA ]
[10] D. Kleyko, D. A. Rachkovskij, E. Osipov and A. Rahimi. A survey on hyperdimensional computing aka vector symbolic architectures : Part I: Models and data transformations. ACM Computing Surveys, 55(6), 2023 [ BibTeX | DiVA ]
[11] A. Srivastava, A. Rastogi and D. Kleyko. Beyond the imitation game : Quantifying and extrapolating the capabilities of language models. Transactions on Machine Learning Research, 5:1-95, 2023 [ BibTeX | DiVA ]
[12] 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. 2023 [ BibTeX | DiVA ]
[13] D. Kleyko, C. Bybee, P. C. Huang, C. J. Kymn, B. A. Olshausen, E. P. Frady and F. T. Sommer. Efficient decoding of compositional structure in holistic representations. Neural Computation, 35(7):1159-1186, 2023 [ BibTeX | DiVA ]
[14] C. Bybee, D. Kleyko, D. E. Nikonov, A. Khosrowshahi, B. A. Olshausen and F. T. Sommer. Efficient optimization with higher-order ising machines. Nature Communications, 14(1), 2023 [ BibTeX | DiVA ]
[15] D. Kleyko, G. Karunaratne, J. M. Rabaey, A. Sebastian and A. Rahimi. Generalized key-value memory to flexibly adjust redundancy in memory-augmented networks. IEEE Transactions on Neural Networks and Learning Systems, 34(12):10993-10998, 2023 [ BibTeX | DiVA ]
[16] K. Dhole, D. Kleyko and Y. Zhang. NL-augmenter : A framework for task-sensitive natural language augmentation. Northern European Journal of Language Technology (NEJLT), 9(1):1-41, 2023 [ BibTeX | DiVA ]
[17] J. L. Teeters, D. Kleyko, P. Kanerva and B. A. Olshausen. On separating long- and short-term memories in hyperdimensional computing. Frontiers in Neuroscience, 16, 2023 [ BibTeX | DiVA ]
[18] M. Heddes, I. Nunes, P. Vergés, D. Kleyko, D. Abraham, T. Givargis, A. Nicolau and A. Veidenbaum. Torchhd : An open source python library to support research on hyperdimensional computing and vector symbolic architectures. Journal of machine learning research, 24(255):1-10, 2023 [ BibTeX | DiVA ]
[19] E. P. Frady, D. Kleyko and F. T. Sommer. Variable binding for sparse distributed representations : theory and applications. IEEE Transactions on Neural Networks and Learning Systems, 34(5):2191-2204, 2023 [ BibTeX | DiVA ]
[20] D. Kleyko, E. Frady and F. Sommer. Cellular automata can reduce memory requirements of collective-state computing. IEEE Transactions on Neural Networks and Learning Systems, 33(6):2701-2713, 2022 [ BibTeX | DiVA ]
[21] E. P. Frady, D. Kleyko, C. J. Kymn, B. A. Olshausen and F. T. Sommer. Computing on functions using randomized vector representations (in brief). In NICE '22 : Proceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference, pages 115-122, 2022 [ BibTeX | DiVA ]
[22] P. C. Huang, D. Kleyko, J. M. Rabaey, B. A. Olshausen and P. Kanerva. Computing with hypervectors for efficient speaker identification. , pages 1-5, 2022 [ BibTeX | DiVA ]
[23] A. Rosato, M. Panella, E. Osipov and D. Kleyko. Few-shot federated learning in randomized neural networks via hyperdimensional computing. In 2022 International Joint Conference on Neural Networks (IJCNN) : Proceedings 2022 [ BibTeX | DiVA ]
[24] D. Kleyko, E. Frady, M. Kheffache and E. Osipov. Integer echo state networks : efficient reservoir computing for digital hardware. IEEE Transactions on Neural Networks and Learning Systems, 33(4):1688-1701, 2022 [ BibTeX | DiVA ]
[25] D. Kleyko, C. Bybee, C. Kymn, B. Olshausen, A. Khosrowshahi, D. E. Nikonov, F. T. Sommer and E. P. Frady. Integer factorization with compositional distributed representations. In NICE '22 : Proceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference, pages 73-80, 2022 [ BibTeX | DiVA ]
[26] D. A. Rachkovskij and D. Kleyko. Recursive Binding for Similarity-Preserving Hypervector Representations of Sequences. In 2022 International Joint Conference on Neural Networks (IJCNN) : Proceedings 2022 [ BibTeX | DiVA ]
[27] D. Kleyko, M. Davies, E. P. Frady, P. Kanerva, S. J. Kent, B. A. Olshausen, E. Osipov, J. M. Rabaey, D. A. Rachkovskij, A. Rahimi and F. T. Sommer. Vector symbolic architectures as a computing framework for emerging hardware. Proceedings of the IEEE, 110(10):1538-1571, 2022 [ BibTeX | DiVA ]
[28] E. Paxon Frady, D. Kleyko, C. J. Kymn, B. A. Olshausen and F. T. Sommer. Computing on Functions Using Randomized Vector Representations. , pages 33, 2021 [ BibTeX | DiVA ]
[29] D. Kleyko, M. Kheffache, E. P. Frady, U. Wiklund and E. Osipov. Density encoding enables resource-efficient randomly connected neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(8):3777-3783, 2021 [ BibTeX | DiVA ]
[30] C. Diao, D. Kleyko, J. M. Rabaey and B. A. Olshausen. Generalized learning vector quantization for classification in randomized neural networks and hyperdimensional computing. In 2021 International Joint Conference on Neural Networks (IJCNN), pages 1-9, 2021 [ BibTeX | DiVA ]
[31] A. Rosato, M. Panella and D. Kleyko. Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks. In 2021 International Joint Conference on Neural Networks (IJCNN) : Proceedings 2021 [ BibTeX | DiVA ]
[32] P. Alonso, K. Shridhar, D. Kleyko, E. Osipov and M. Liwicki. HyperEmbed : Tradeoffs between resources and performance in NLP Tasks with hyperdimensional computing enabled embedding of n-gram statistics. In 2021 International Joint Conference on Neural Networks (IJCNN) : Proceedings 2021 [ BibTeX | DiVA ]
[33] A. Rosato, M. Panella, E. Osipov and D. Kleyko. On effects of compression with hyperdimensional computing in distributed randomized neural networks. In Advances in Computational Intelligence : 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event, June 16–18, 2021, Proceedings, Part II, 12862:155-167, 2021 [ BibTeX | DiVA ]
[34] D. Kleyko, E. Osipov and U. Wiklund. A comprehensive study of complexity and performance of automatic detection of atrial fibrillation : Classification of long ECG recordings based on the PhysioNet computing in cardiology challenge 2017. Biomedical Engineering & Physics Express, 6(2), 2020 [ BibTeX | DiVA ]
[35] D. Rutqvist, D. Kleyko and F. Blomstedt. An automated machine learning approach for smart waste management systems. IEEE Transactions on Industrial Informatics, 16(1):384-392, 2020 [ BibTeX | DiVA ]
[36] D. Kleyko, A. Rahimi, R. W. Gayler and E. Osipov. Autoscaling bloom filter : controlling trade-off between true and false positives. Neural Computing & Applications, 32(8):3675-3684, 2020 [ BibTeX | DiVA ]
[37] D. Kleyko, R. W. Gayler and E. Osipov. Commentaries on Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception [Science Robotics Vol. 4 Issue 30 (2019) 1-10. 2020 [ BibTeX | DiVA ]
[38] H. Jain, A. Agarwal, K. Shridhar and D. Kleyko. End to end binarized neural networks for text classification. , pages 29-34, 2020 [ BibTeX | DiVA ]
[39] D. Kleyko, E. Osipov and U. Wiklund. A hyperdimensional computing framework for analysis of cardiorespiratory synchronization during paced deep breathing. IEEE Access, 7:34403-34415, 2019 [ BibTeX | DiVA ]
[40] D. Kleyko, E. Osipov, D. De Silva, U. Wiklund, V. Vyatkin and D. Alahakoon. Distributed representation of n-gram statistics for boosting self-organizing maps with hyperdimensional computing. In Perspectives of system informatics : 12th International Andrei P. Ershov Informatics Conference, PSI 2019, Novosibirsk, Russia, July 2–5, 2019, Revised Selected Papers, pages 64-79, 2019 [ BibTeX | DiVA ]
[41] D. Kleyko, E. Osipov, D. De Silva, U. Wiklund and D. Alahakoon. Integer Self-Organizing Maps for Digital Hardware. In 2019 International Joint Conference on Neural Networks (IJCNN) 2019 [ BibTeX | DiVA ]
[42] N. Karvonen, J. Nilsson, D. Kleyko and L. L. Jimenez. Low-Power classification using FPGA : An approach based on cellular automata, neural networks, and hyperdimensional computing. In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), pages 370-375, 2019 [ BibTeX | DiVA ]
[43] P. V. Krasheninnikov, O. G. Melent’ev, D. Kleyko and A. G. Shapin. Parameter estimation for the resulting logical channel formed by minimizing channel switching. Automation and remote control, 80(2):278-285, 2019 [ BibTeX | DiVA ]
[44] N. Lyamin, D. Kleyko, Q. Delooz and A. Vinel. Real-Time jamming DoS Detection in Safety-Critical V2V C-ITS using data mining. IEEE Communications Letters, 23(3):442-445, 2019 [ BibTeX | DiVA ]
[45] T. Bandaragoda, D. De Silva, D. Kleyko, E. Osipov, U. Wiklund and D. Alahakoon. Trajectory clustering of road traffic in urban environments using incremental machine learning in combination with hyperdimensional computing. In 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pages 1664-1670, 2019 [ BibTeX | DiVA ]
[46] N. Karvonen and D. Kleyko. A domain knowledge-based solution for human activity recognition : The UJA Dataset Analysis. In Proceedings, 2018, UCAmI 2018, 2(2(19)):1-8, 2018 [ BibTeX | DiVA | PDF ]
[47] E. P. Frady, D. Kleyko and F. T. Sommer. A theory of sequence indexing and working memory in recurrent neural networks. Neural Computation, 30(6):1449-1513, 2018 [ BibTeX | DiVA ]
[48] N. Lyamin, D. Kleyko, Q. Delooz and A. Vinel. AI-based malicious network traffic detection in VANETs. IEEE Network, 32(6):15-21, 2018 [ BibTeX | DiVA ]
[49] D. Kleyko, A. Rahimi, D. A. Rachkovskij, E. Osipov and J. M. Rabaey. Classification and recall with binary hyperdimensional computing : Tradeoffs in choice of density and nmapping characteristics. IEEE Transactions on Neural Networks and Learning Systems, 29(12):5880-5898, 2018 [ BibTeX | DiVA ]
[50] A. Abdukalikova, D. Kleyko, E. Osipov and U. Wiklund. Detection of atrial fibrillation from short ECGs : Minimalistic complexity analysis for feature-based classifiers. In Computing in Cardiology 2018 : Proceedings, 45(45), 2018 [ BibTeX | DiVA ]
[51] D. Kleyko, E. Osipov, N. Papakonstantinou and V. Vyatkin. Hyperdimensional computing in industrial systems : The use-case of distributed fault isolation in a power plant. IEEE Access, 6:30766-30777, 2018 [ BibTeX | DiVA ]
[52] D. Kleyko and E. Osipov. No two brains are alike : cloning a hyperdimensional associative memory using cellular automata computations. In Biologically Inspired Cognitive Architectures (BICA) for Young Scientists : Proceedings of the First International Early Research Career Enhancement School on BICA and Cybersecurity (FIERCES 2017), pages 91-100, 2018 [ BibTeX | DiVA ]
[53] D. Wedekind, D. Kleyko, E. Osipov, H. Malberg, S. Zaunseder and U. Wiklund. Robust methods for automated selection of cardiac signals after blind source separation. IEEE Transactions on Biomedical Engineering, 65(10):2248-2258, 2018 [ BibTeX | DiVA ]
[54] D. Kleyko. Vector symbolic architectures and their applications : Computing with random vectors in a hyperdimensional space. Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Luleå, Sweden, Ph.D. Thesis, 2018 [ BibTeX | DiVA ]
[55] D. Kleyko. Vector symbolic architectures and their applications : Computing with random vectors in a hyperdimensional space. Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Luleå, Sweden, Ph.D. Thesis, 2018 [ BibTeX | DiVA ]
[56] A. Rahimi, S. Datta, D. Kleyko, E. P. Frady, B. Olshausen, P. Kanerva and J. M. Rabaey. High-Dimensional Computing as a Nanoscalable Paradigm. IEEE Transactions on Circuits and Systems Part 1: Regular Papers, 64(9):2508-2521, 2017 [ BibTeX | DiVA ]
[57] D. Kleyko, E. Osipov, A. Senior, A. I. Khan and Y. A. Sekercioglu. Holographic graph neuron : A bioinspired architecture for pattern processing. IEEE Transactions on Neural Networks and Learning Systems, 28(6):1250-1262, 2017 [ BibTeX | DiVA ]
[58] D. Kleyko, S. Khan, E. Osipov and S. P. Yong. Modality classification of medical images with distributed representations based on cellular automata reservoir computing. In 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) : Proceedings, pages 1053-1056, 2017 [ BibTeX | DiVA ]
[59] V. I. Grytsenko, D. A. Rachkovskij, A. A. Frolov, R. Gayler, D. Kleyko and E. Osipov. Neural distributed autoassociative memories : A survey. Cybernetics and Computer Engineering, 188(2):5-35, 2017 [ BibTeX | DiVA ]
[60] E. Osipov, D. Kleyko and A. Shapin. An approach for self-adaptive path loss modelling for positioning in underground environments. International Journal of Antennas and Propagation 2016 [ BibTeX | DiVA ]
[61] D. Kleyko, E. Osipov and D. A. Rachkovskij. Modification of Holographic Graph Neuron using Sparse Distributed Representations. In Procedia Computer Science, 88(88):39-45, 2016 [ BibTeX | DiVA ]
[62] D. Kleyko. Pattern recognition with vector symbolic architectures. , pages 136, 2016 [ BibTeX | DiVA ]
[63] D. Kleyko, E. Osipov and R. W. Gayler. Recognizing Permuted Words with Vector Symbolic Architectures : A Cambridge Test for Machines. , 88(Vol. 88):169-175, 2016 [ BibTeX | DiVA ]
[64] D. Wedekind, D. Kleyko, E. Osipov, H. Malberg, S. Zaunseder and U. Wiklund. Sparse coding of cardiac signals for automated component selection after blind source separation. , pages 785-788, 2016 [ BibTeX | DiVA ]
[65] D. Kleyko, R. Hostettler, N. Lyamin, W. Birk, U. Wiklund and E. Osipov. Vehicle classification using road side sensors and feature-free data smashing approach. In 2016 Ieee 19Th International Conference On Intelligent Transportation Systems (Itsc), pages 1988-1993, 2016 [ BibTeX | DiVA ]
[66] D. Kleyko, R. Hostettler, W. Birk and E. Osipov. Comparison of machine learning techniques for vehicle classification using road side sensors. In 2015 IEEE 18th International Conference on Intelligent Transportation Systems : Proceedings, pages 572-577, 2015 [ BibTeX | DiVA ]
[67] D. Kleyko, E. Osipov, N. Papakonstantinou, V. Vyatkin and A. Mousavi. Fault detection in the hyperspace : towards intelligent automation systems. In 2015 IEEE 13th International Conference on Industrial Informatics (INDIN) : Proceedings, pages 1219-1224, 2015 [ BibTeX | DiVA ]
[68] D. Kleyko, E. Osipov, M. Björk, H. Toresson and A. Öberg. Fly-The-Bee : A Game Imitating Concept Learning in Bees. , 71(Vol. 71):25-30, 2015 [ BibTeX | DiVA ]
[69] D. Kleyko, E. Osipov, R. W. Gayler, A. I. Khan and A. G. Dyer. Imitation of honey bees' concept learning processes using Vector Symbolic Architectures. Biologically Inspired Cognitive Architectures, 14:57-72, 2015 [ BibTeX | DiVA ]
[70] D. Kleyko and E. Osipov. Brain-like classifier of temporal patterns. In 2014 International Conference on Computer and Information Sciences (ICCOINS), 3-5 June 2014 : Proceedings, pages 1-6, 2014 [ BibTeX | DiVA ]
[71] S. Balasubramaniam, N. Lyamin, D. Kleyko, M. Skurnik, A. Vinel and Y. Koucheryavy. Exploiting bacterial properties for multi-hop nanonetworks. IEEE Communications Magazine, 52(7):184-191, 2014 [ BibTeX | DiVA ]
[72] D. Kleyko, N. Lyamin and E. Osipov. Modified algorithm of dynamic frequency hopping (DFH) in the IEEE 802.22 standard. In Multiple access communications : 7th International Workshop, MACOM 2014, Halmstad, Sweden, August 27-28, 2014, Proceedings, pages 75-83, 2014 [ BibTeX | DiVA | PDF ]
[73] D. Kleyko and E. Osipov. On bidirectional transitions between localist and distributed representations : The case of common substrings search using Vector Symbolic Architecture. , 41:104-113, 2014 [ BibTeX | DiVA ]
[74] D. Kleyko, E. Osipov, S. Patil, V. Vyatkin and Z. Pang. On methodology of implementing distributed function block applications using TinyOS WSN nodes. In Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA) 2014 [ BibTeX | DiVA ]
[75] O. G. Melent’ev and D. Kleyko. Computing the parameters of the discrete channel resulting under frequency hopping in the general case. Automation and remote control, 74(7):1128-1131, 2013 [ BibTeX | DiVA ]
[76] D. Kleyko, N. Lyamin, E. Osipov and L. Riliskis. Dependable MAC layer architecture based on holographic data representation using hyper-dimensional binary spatter codes. In Multiple access communications : 5th International Workshop, MACOM 2012, Maynooth, Ireland, November 19-20, 2012. Proceedings, pages 134-145, 2012 [ BibTeX | DiVA ]
[77] E. Osipov, L. Riliskis, D. Kleyko and N. Lyamin. Packet-less medium access approach for dependable wireless event passing in highly noisy environments. , pages 10, 2012 [ BibTeX | DiVA ]