Skip to main content

Learning from Few Examples with Nonlinear Feature Maps

  • 213 Accesses

Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 711)

Abstract

In this work we consider the problem of data classification in post-classical settings where the number of training examples consists of mere few data points. We explore the phenomenon and reveal key relationships between dimensionality of AI model’s feature space, non-degeneracy of data distributions, and the model’s generalisation capabilities. The main thrust of our present analysis is on the influence of nonlinear feature transformations mapping original data into higher- and possibly infinite-dimensional spaces on the resulting model’s generalisation capabilities. Subject to appropriate assumptions, we establish new relationships between properties of nonlinear feature transformation maps and the probabilities to learn successfully from few presentations.

Keywords

  • Few-Shot Learning
  • Kernel Learning
  • Learning from Low-Sample High-Dimensional Data

I.Y. Tyukin—The work was supported by the UKRI Turing AI Fellowship EP/V025295/2 and the UKRI Trustworthy Autonomous Systems in Verifiability node EP/V026801/2.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   219.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   279.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Bartlett, P.L., Long, P.M., Lugosi, G., Tsigler, A.: Benign overfitting in linear regression. Proc. National Acad. Sci. 117(48), 30063–30070 (2020)

    CrossRef  MathSciNet  MATH  Google Scholar 

  2. Gorban, A.N., Grechuk, B., Mirkes, E.M., Stasenko, S.V., Tyukin, I.Y.: High-dimensional separability for one-and few-shot learning. Entropy 23(8), 1090 (2021)

    CrossRef  MathSciNet  Google Scholar 

  3. Gorban, A.N., Tyukin, I.Y., Prokhorov, D.V., Sofeikov, K.I.: Approximation with random bases: pro et contra. Inf. Sci. 364–365, 129–145 (2016)

    CrossRef  MATH  Google Scholar 

  4. Kainen, P.C., Kůrková, V.: Quasiorthogonal dimension. In: Kosheleva, O., Shary, S.P., Xiang, G., Zapatrin, R. (eds.) Beyond Traditional Probabilistic Data Processing Techniques: Interval, Fuzzy etc. Methods and Their Applications. SCI, vol. 835, pp. 615–629. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-31041-7_35

    CrossRef  Google Scholar 

  5. Kainen, P.C., Kurkova, V.: Quasiorthogonal dimension of Euclidian spaces. Appl. Math. Lett. 6(3), 7–10 (1993)

    CrossRef  MathSciNet  MATH  Google Scholar 

  6. Ledoux, M.: The concentration of measure phenomenon. Am. Math. Soc. Number 89 (2001)

    Google Scholar 

  7. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

    Google Scholar 

  8. Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)

    Google Scholar 

  9. Tyukin, I.Y., Gorban, A.N., Alkhudaydi, M.H., Zhou, Q.: Demystification of few-shot and one-shot learning. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2021)

    Google Scholar 

  10. Tyukin, I.Y., Gorban, A.N., Grechuk, B., Green, S.: Kernel stochastic separation theorems and separability characterizations of kernel classifiers. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2019)

    Google Scholar 

  11. Tyukin, I.Y., Gorban, A.N., Green, S., Prokhorov, D.: Fast construction of correcting ensembles for legacy artificial intelligence systems: algorithms and a case study. Inf. Sci. 485, 230–247 (2019)

    CrossRef  MathSciNet  MATH  Google Scholar 

  12. Tyukin, I.Y., Gorban, A.N., McEwan, A.A., Meshkinfamfard, S., Tang, L.: Blessing of dimensionality at the edge and geometry of few-shot learning. Inf. Sci. 564, 124–143 (2021)

    CrossRef  MathSciNet  Google Scholar 

  13. Tyukin, I.Y., Gorban, A.N., Sofeykov, K.I., Romanenko, I.: Knowledge transfer between artificial intelligence systems. Front. Neurorobotics 12, 49 (2018)

    CrossRef  Google Scholar 

  14. Vapnik, V.N.: An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988–999 (1999)

    CrossRef  Google Scholar 

  15. Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, pp. 3630–3638 (2016)

    Google Scholar 

  16. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016)

  17. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64(3), 107–115 (2021)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ivan Y. Tyukin .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Tyukin, I.Y., Sutton, O., Gorban, A.N. (2023). Learning from Few Examples with Nonlinear Feature Maps. In: Arai, K. (eds) Intelligent Computing. SAI 2023. Lecture Notes in Networks and Systems, vol 711. Springer, Cham. https://doi.org/10.1007/978-3-031-37717-4_15

Download citation