Ivan Tyukin

Professor of Mathematics, King's College London

ivan.tyukin@kcl.ac.uk

Biography

Professor Ivan Tyukin is an expert in the mathematical foundations of Artificial Intelligence (AI) and learning systems, Machine Learning, mathematical modelling, adaptive systems, inverse problems with nonconvex and nonlinear parameterization, data analytics, and computer vision.

Professor Tyukin has been awarded a prestigious Turing AI Acceleration Fellowship to lead innovative and creative AI research with transformative impact. He is a member of the IFAC Technical Committee on Adaptive and Learning Systems, an Editor of Communications in Nonlinear Science and Numerical Simulations, and is a member of the All Party Parliamentary Group on AI’s data governance task force which examines the economic, social, and ethical implications of AI. He has a broad network of academic and industrial collaborators includes strategic UK sectors such as public safety and security, health technologies, space and Earth Observation, and manufacturing.

Professor Tyukin’s recent work focuses on creating a theory and practice for developing AI systems that are provably robust, resilient, certifiable, trustworthy, human-centric and data-driven. The theory will enable the creation of new-generation AI systems which are certifiably stable, secure, adaptive and maintainable. These systems will be prepared to handle the challenges of adversarial attacks and data inconsistences, uncertainties, and bias inherent within any empirical data. This will enable new gold standard methods and tools in tasks that are currently heavily reliant upon non-deterministic human input to have long-term transformation.

Recent Publications

M. R. Mousavi, A. Cavalcanti, M. Fisher, L. Dennis, R. Hierons, B. Kaddouh, E. L. Law, R. Richardson, J. O. Ringer, I. Y. Tyukin, and J. Woodcock (2023). Trustworthy Autonomous Systems Through Verifiability, Computer 56(2), pages 40-47.
S. Wang, A. M. S. E. K. Abdelaty, K. Parke, J. R. Arnold, G. P. McCann, and I. Y. Tyukin (2023). MyI-Net: Fully Automatic Detection and Quantification of Myocardial Infarction from Cardiovascular MRI Images, Entropy 25(3).
A. Markfort, A. Baranov, T. M. Conneely, A. Duran, J. Milnes, A. Mudrov, J. Lapington, and I. Y. Tyukin (2023). Utilising machine learning algorithms for high speed data processing of a single photon counting 256 channel PMT with a timing resolution of 60 ps, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 1047.
Q. Zhou, O. J. Sutton, Y. Zhang, A. N. Gorban, V. A. Makarov, and I. Y. Tyukin (2023). Neuromorphic tuning of feature spaces to overcome the challenge of low-sample high-dimensional data, International Joint Conference On Neural Networks (IJCNN) 2023.
I. Y. Tyukin, O. J. Sutton, and A. N. Gorban (2023). Learning from few examples with nonlinear feature maps, Science and Information Conference (2023) vol 711, pp 210-225, Springer, Cham. Winner of best paper award.
O. J. Sutton, A. N. Gorban, and I. Y. Tyukin (2023). A geometric view on the role of nonlinear feature maps in few-shot learning, Geometric Science of Information (GSI) 2023 vol 14071, pp 560-568, Springer, Cham.
O. J. Sutton, Q. Zhou, A. N. Gorban, and I. Y. Tyukin (2023). Relative intrinsic dimensionality is intrinsic to learning, International Conference on Artificial Neural Networks (ICANN) 2023 vol 14254, pp 516-529, Springer, Cham.
A. Bastounis, A. N. Gorban, A. C. Hansen, D. J. Higham, D. Prokhorov, O. J. Sutton, I. Y. Tyukin, and Q. Zhou (2023). The boundaries of verifiable accuracy, robustness, and generalisation in deep learning, International Conference on Artificial Neural Networks (ICANN) 2023 vol 14254, pp 530-541, Springer, Cham.
Y. Liu, L. Guo, V. A. Makarov, Y. Huang, A. N. Gorban, E. Mirkes, and I. Y. Tyukin (2023). Agile gesture recognition for capacitive sensing devices: adapting on-the-job, arXiv 2305.07624.
D. Lukashevich, G. V. Ovchinnikov, I. Y. Tyukin, S. A. Matveev, and N. V. Brilliantov (2022). Data-Driven Approach for Modeling Coagulation Kinetics, Computational Mathematics and Modeling 33(3), 310-318.
A. Markfort, A. Baranov, T. M. Conneely, A. Duran, J. Lapington, J. Milnes, W. Moore, A. Mudrov, and I. Y. Tyukin (2022). Investigating machine learning solutions for a 256 channel TCSPC camera with sub-70 ps single photon timing per channel at data rates >10 Gbps, Journal of Instrumentation Volume 17, Issue 7, C07023.
D. van Helden, E. Mirkes, I. Y. Tyukin, and P. Allison (2022). The Arch-I-Scan Project: artificial intelligence and 3D simulation for developing new approaches to Roman foodways, Journal of Computer Applications in Archaeology 5(1), 78-95.
J. Barker, X. Li, S. Khavandi, D. Koeckerling, A. Mavilakandy, C. Pepper, V. Bountziouka, L. Chen, A. Kotb, I. Antoun, J. Mansir, K. Smith-Byrne, F. S. Schlindwein, H. Dhutia, I. Y. Tyukin, W. B. Nicolson, and G. Andre Ng (2022). Machine learning in sudden cardiac death risk prediction: a systematic review, Europace 24(11), pages 1777-1787.
Q. Zhou, A. N. Gorban, E. M. Mirkes, J. Bac, A. Zinovyev, and I. Y. Tyukin (2022). Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation, International Joint Conference On Neural Networks (IJCNN) 2022.
G. D. Leete, A. N. Gorban, and I. Y. Tyukin (2022). Fast situation-based correction of AI systems, 4th International Conference on Industrial Artificial Intelligence (ICIAI).
O. J. Sutton, A. N. Gorban, and I. Y. Tyukin (2022). Towards a mathematical understanding of learning from few examples with nonlinear feature maps, arXiv 2211.03607.
B. Grechuk, A. N. Gorban, and I. Y. Tyukin (2021). General stochastic separation theorems with optimal bounds, Neural Networks 138, pages 33-56.
I. Y. Tyukin, A. N. Gorban, A. A. McEwan, S. Meshkinfamfard, and L. Tang (2021). Blessing of dimensionality at the edge and geometry of few-shot learning, Information Sciences 564, pages 124-143.
S. Wang, M. E. Celebi, Y. Zhang, X. Yu, S. Lu, X. Yao, Q. Zhou, M. Miguel, Y. Tian, J. M. Gorriz, and I. Y. Tyukin (2021). Advances in Data Preprocessing for Biomedical Data Fusion: An Overview of the Methods, Challenges, and Prospects, Information Fusion 76, pages 376-421.
A. N. Gorban, B. Grechuk, E. M. Mirkes, S. Stasenko V, and I. Y. Tyukin (2021). High-Dimensional Separability for One- and Few-Shot Learning, Entropy 23(8).
S. J. N. Jareno, D. P. van Helden, E. M. Mirkes, I. Y. Tyukin, and P. M. Allison (2021). Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery, Entropy 23(9).
J. Bac, E. M. Mirkes, A. N. Gorban, I. Y. Tyukin, and A. Zinovyev (2021). Scikit-Dimension: A Python Package for Intrinsic Dimension Estimation, Entropy 23(10).
I. Y. Tyukin, A. N. Gorban, M. H. Alkhudaydi, and Q. Zhou (2021). Demystification of Few-shot and One-shot Learning, 2021 International Joint Conference On Neural Networks (IJCNN).
U. C. Turker, R. M. Hierons, M. R. Mousavi, and I. Y. Tyukin (2021). Efficient state synchronisation in model-based testing through reinforcement learning, 2021 36th IEEE/ACM International Conference On Automated Software Engineering ASE 2021.
A. N. Gorban, V. A. Makarov, and I. Y. Tyukin (2020). High-Dimensional Brain in a High-Dimensional World: Blessing of Dimensionality, Entropy 22(1).
A. N. Gorban, E. M. Mirkes, and I. Y. Tyukin (2020). How Deep Should be the Depth of Convolutional Neural Networks: a Backyard Dog Case Study, Cognitive Computation 12(2, SI), pages 388-397.
C. Calvo Tapia, I. Y. Tyukin, and V. A. Makarov (2020). Universal principles justify the existence of concept cells, Scientific Reports 10(1).
N. V. Brilliantov, H. Abutuqayqah, I. Y. Tyukin, and S. A. Matveev (2020). Swirlonic state of active matter, Scientific Reports 10(1).
S. Wang, G. McCann, and I. Y. Tyukin (2020). Myocardial Infarction Detection and Quantification Based on a Convolution Neural Network with Online Error Correction Capabilities, 2020 International Joint Conference On Neural Networks (IJCNN).
I. Y. Tyukin, D. J. Higham, and A. N. Gorban (2020). On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems, 2020 International Joint Conference On Neural Networks (IJCNN).
R. Fenwick, H. Boecsh, and I. Y. Tyukin (2020). Neural Networks for the Retrieval of Methane from the Sentinel-5 Precursor Satellite, 2020 International Joint Conference On Neural Networks (IJCNN).
E. Wilson, T. M. Conneely, A. Mudrov, and I. Y. Tyukin (2019). Implementation of the Prony Method for Signal Deconvolution, IFAC Papersonline 52(29), pages 269-273.
A. N. Gorban, R. Burton, I. Romanenko, and I. Y. Tyukin (2019). One-trial correction of legacy AI systems and stochastic separation theorems, Information Sciences 484, pages 237-254.
I. Y. Tyukin, A. N. Gorban, S. Green, and D. Prokhorov (2019). Fast construction of correcting ensembles for legacy Artificial Intelligence systems: Algorithms and a case study, Information Sciences 485, pages 230-247.
I. Y. Tyukin, D. Iudin, F. Iudin, T. Tyukina, V. Kazantsev, I. Mukhina, and A. N. Gorban (2019). Simple model of complex dynamics of activity patterns in developing networks of neuronal cultures, PLoS ONE 14(6).
A. N. Gorban, V. A. Makarov, and I. Y. Tyukin (2019). Symphony of high-dimensional brain Reply to comments on ''The unreasonable effectiveness of small neural ensembles in high-dimensional brain'', Physics Of Life Reviews 29, pages 115-119.
A. N. Gorban, V. A. Makarov, and I. Y. Tyukin (2019). The unreasonable effectiveness of small neural ensembles in high-dimensional brain, Physics Of Life Reviews 29, pages 55-88.
I. Y. Tyukin, A. N. Gorban, C. Calvo, J. Makarova, and V. A. Makarov (2019). High-Dimensional Brain: A Tool for Encoding and Rapid Learning of Memories by Single Neurons, Bulletin Of Mathematical Biology 81(11, SI), pages 4856-4888.
I. Y. Tyukin, A. N. Gorban, B. Grechuk, and S. Green (2019). Kernel Stochastic Separation Theorems and Separability Characterizations of Kernel Classifiers, 2019 International Joint Conference On Neural Networks (IJCNN).
I. Y. Tyukin, A. N. Gorban, A. McEwan, and S. Meshkinfamfard (2019). Bringing the Blessing of Dimensionality to the Edge, 2019 1st International Conference On Industrial Artificial Intelligence (IAI 2019).
C. Calvo Tapia, I. Y. Tyukin, and V. A. Makarov (2018). Fast social-like learning of complex behaviors based on motor motifs, Physical Review E 97(5).
I. Y. Tyukin, A. N. Gorban, K. I. Sofeykov, and I. Romanenko (2018). Knowledge Transfer Between Artificial Intelligence Systems, Frontiers In Neurorobotics 12.
P. N. Suganthan, S. Mitra, and I. Y. Tyukin (2018). Preface special issue on non-iterative approaches in learning, Applied Soft Computing 70, pages 947-950.
I. Y. Tyukin, A. N. Gorban, D. Prokhorov V, and S. Green (2018). Efficiency of Shallow Cascades for Improving Deep Learning AI Systems, 2018 International Joint Conference On Neural Networks (IJCNN).
S. Meshkinfamfard, A. N. Gorban, and I. Y. Tyukin (2018). Tackling Rare False-Positives in Face Recognition: a Case Study, IEEE 20th International Conference On High Performance Computing And Communications / IEEE 16th International Conference On Smart City / IEEE 4th International Conference On Data Science And Systems (HPCC/Smartcity/DSS).
N. Jarman, E. Steur, C. Trengove, I. Y. Tyukin, and C. van Leeuwen (2017). Self-organisation of small-world networks by adaptive rewiring in response to graph diffusion, Scientific Reports 7.
D. I. Iudin, I. Y. Tyukin, A. N. Gorban, F. D. Iudin, V. B. Kazantsev, I. V. Muhina, and T. T. Tyukina (2016). Simple model of complex bursting dynamics in developing networks of neuronal cultures, IFAC Papersonline 49(14), pages 68-73.
A. N. Gorban, I. Y. Tyukin, and I. Romanenko (2016). The Blessing of Dimensionality: Separation Theorems in the Thermodynamic Limit, IFAC Papersonline 49(24), pages 64-69.
A. N. Gorban, I. Y. Tyukin, D. V. Prokhorov, and K. I. Sofeikov (2016). Approximation with random bases: Pro et Contra, Information Sciences 364, pages 129-145.
G. Fridman, J. Levesley, I. Y. Tyukin, and D. Wunsch (2015). Preface, Mathematical Modelling Of Natural Phenomena 10(3), pages 1-5.
I. Prokin, I. Y. Tyukin, and V. Kazantsev (2015). Phase Selective Oscillations in Two Noise Driven Synaptically Coupled Spiking Neurons, International Journal Of Bifurcation And Chaos 25(7).
N. Jarman, C. Trengove, E. Steur, I. Y. Tyukin, and C. van Leeuwen (2014). Spatially constrained adaptive rewiring in cortical networks creates spatially modular small world architectures, Cognitive Neurodynamics 8(6), pages 479-497.
A. N. Gorban, I. Y. Tyukin, and H. Nijmeijer (2014). Further Results on Lyapunov-Like Conditions of Forward Invariance and Boundedness for a Class of Unstable Systems, 2014 IEEE 53Rd Annual Conference On Decision And Control (CDC).
I. Y. Tyukin, E. Steur, H. Nijmeijer, and C. van Leeuwen (2013). Adaptive observers and parameter estimation for a class of systems nonlinear in the parameters, Automatica 49(8), pages 2409-2423.
P. Jurica, S. Gepshtein, I. Y. Tyukin, and C. van Leeuwen (2013). Sensory Optimization by Stochastic Tuning, Psychological Review 120(4), pages 798-816.
V. Kazantsev, and I. Y. Tyukin (2012). Adaptive and Phase Selective Spike Timing Dependent Plasticity in Synaptically Coupled Neuronal Oscillators, PLoS ONE 7(3).
I. Y. Tyukin, E. Steur, H. Nijmeijer, D. Fairhurst, I. Song, A. Semyanov, and C. Van Leeuwen (2010). State And Parameter Estimation For Canonic Models Of Neural Oscillators, International Journal Of Neural Systems 20(3), pages 193-207.
I. Y. Tyukin, T. Tyukina, and C. van Leeuwen (2009). Invariant template matching in systems with spatiotemporal coding: A matter of instability, Neural Networks 22(4), pages 425-449.
E. Steur, I. Y. Tyukin, and H. Nijmeijer (2009). Semi-passivity and synchronization of diffusively coupled neuronal oscillators, Physica D-Nonlinear Phenomena 238(21), pages 2119-2128.
I. Y. Tyukin, and D. V. Prokhorov (2009). Feasibility of random basis function approximators for modeling and control, 2009 IEEE Control Applications Cca \& Intelligent Control (Isic), Vols 1-3.
I. Y. Tyukin, E. Steur, H. Nijmeijer, and C. Van Leeuwen (2008). Nonuniform small-gain theorems for systems with unstable invariant sets, SIAM Journal On Control And Optimization 47(2), pages 849-882.
I. Y. Tyukin, D. Prokhorov, and C. Van Leeuwen (2008). Adaptive classification of temporal signals in fixed-weight recurrent neural networks: An existence proof, Neural Computation 20(10), pages 2564-2596.