Blessing of dimensionality at the edge and geometry of few-shot learning

Journal article


Tyukin, Ivan Y., Gorban, Alexander N., McEwan, Alistair A., Meshkinfamfard, Sepehr and Tang, Lixin 2021. Blessing of dimensionality at the edge and geometry of few-shot learning. Information Sciences. 564, pp. 124-143. https://doi.org/10.1016/j.ins.2021.01.022
AuthorsTyukin, Ivan Y., Gorban, Alexander N., McEwan, Alistair A., Meshkinfamfard, Sepehr and Tang, Lixin
Abstract

In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a priori quantifiable guarantees – or more specifically remove classification errors – over time. This is distinct from state-of-the-art machine learning, AI, and software approaches. The theory enables building few-shot AI correction algorithms and provides conditions justifying their successful application. Another feature of this approach is that, in the supervised setting, the computational complexity of training is linear in the number of training samples. At the time of classification, the computational complexity is bounded by few inner product calculations. Moreover, the implementation is shown to be very scalable. This makes it viable for deployment in applications where computational power and memory are limited, such as embedded environments. It enables the possibility for fast on-line optimisation using improved training samples. The approach is based on the concentration of measure effects and stochastic separation theorems and is illustrated with an example on the identification faulty processes in Computer Numerical Control (CNC) milling and with a case study on adaptive removal of false positives in an industrial video surveillance and analytics system.

KeywordsControl and Systems Engineering; Theoretical Computer Science; Software; Information Systems and Management; Artificial Intelligence; Computer Science Applications
Year2021
JournalInformation Sciences
Journal citation564, pp. 124-143
PublisherElsevier BV
ISSN0020-0255
Digital Object Identifier (DOI)https://doi.org/10.1016/j.ins.2021.01.022
Web address (URL)hdl:10545/625663
https://www.sciencedirect.com/science/article/pii/S0020025521000499?via%3Dihub
Output statusPublished
Publication dates03 Feb 2021
Publication process dates
Deposited22 Mar 2021, 14:22
Accepted08 Jan 2021
ContributorsUniversity of Leicester, Lobachevsky University, Russia, St Petersburg State Electrotechnical University, Russia, University College London, Northeastern University, China, Norwegian University of Science and Technology, Norway and University of Derby
File
File Access Level
Restricted
Permalink -

https://repository.derby.ac.uk/item/936x1/blessing-of-dimensionality-at-the-edge-and-geometry-of-few-shot-learning

  • 43
    total views
  • 0
    total downloads
  • 18
    views this month
  • 0
    downloads this month

Export as

Related outputs

A Multi-Dataset Characterization of Window-based Hyperparameters for Deep CNN-driven sEMG Pattern Recognition
Kulwa, F., Zhang, H., Samuel, O., Asogbon, M., Scheme, E., Kushaba, R., McEwan, A. and Li, G. 2023. A Multi-Dataset Characterization of Window-based Hyperparameters for Deep CNN-driven sEMG Pattern Recognition. IEEE Transactions on Human-Machine Systems. pp. 1-12. https://doi.org/10.1109/THMS.2023.3329536
An Attention-based Bidirectional LSTM Model for Continuous Cross-subject Estimation of Knee Joint Angle during Running from sEMG Signals
Zangene, A., Samuel, O., Abbasi, A., Nazarpour, K., McEwan, A. and Li, G. 2023. An Attention-based Bidirectional LSTM Model for Continuous Cross-subject Estimation of Knee Joint Angle during Running from sEMG Signals. 45th Annual International Conference of the IEEE, Engineering in Medicine and Biology Society. IEEE. https://doi.org/10.1109/EMBC40787.2023.10340791
Enhanced Deep Transfer Learning Model based on Spatial-Temporal driven Scalograms for Precise Decoding of Motor Intent in Stroke Survivors
Samuel, O., Asogbon, M., Kulwa, F., Zangene, A., Oyemakinde, T., Igbe, T., McEwan, A., Li, Y. and Li, G. 2023. Enhanced Deep Transfer Learning Model based on Spatial-Temporal driven Scalograms for Precise Decoding of Motor Intent in Stroke Survivors. 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE. https://doi.org/10.1109/EMBC40787.2023.10340683
An efficient attention-driven deep neural network approach for continuous estimation of knee joint kinematics via sEMG signals during running
Zangene, A. R., Samuel, O., Abbasi, A., McEwan, A., Asogbon, M. G., Li, G. and Nazarpour, K. 2023. An efficient attention-driven deep neural network approach for continuous estimation of knee joint kinematics via sEMG signals during running. Biomedical Signal Processing and Control. 86 (B), pp. 1-12. https://doi.org/10.1016/j.bspc.2023.105103
A systematic literature review of machine learning applications for community-acquired pneumonia
Lozano-Rojas, Daniel, Free, Robert C., McEwan, Alistair A. and Woltmann, Gerrit 2021. A systematic literature review of machine learning applications for community-acquired pneumonia. in: Lecture Notes in Electrical Engineering Springer.
Bringing the Blessing of Dimensionality to the Edge
Tyukin, Ivan Y., Gorban, Alexander N, McEwan, Alistair and Meshkinfamfard, Sepehr 2019. Bringing the Blessing of Dimensionality to the Edge. IEEE. https://doi.org/10.1109/iciai.2019.8850825