I‑AIMS Institute for Artificial Intelligence
and Mathematical Sciences
/

Artificial neural networks on graded vector spaces

Tanush Shaska

I-AIMS paper 2024-02 · Published in Contemp. Math. 835 (2026), 1–72 · 2026

We develop new artificial neural network models for graded vector spaces, which are suitable when different features in the data have different significance (weights). This is the first time that such models are designed mathematically and they are expected to perform better than neural networks over usual vector spaces, which are the special case when the gradings are all 1s.

MSC classes: Primary 68T07; Secondary 17B70

PDF

References

  1. I. N. Balaba, Isomorphisms of graded rings of linear transformations of graded vector spaces, Chebyshevskiu i Sb. 6 (2005), no. 4(16), 7–24.
  2. Vitalij M. Bondarenko, Linear operators on S-graded vector spaces, 2003, pp. 45–90. Special issue on linear algebra methods in representation theory.
  3. N. Bourbaki, Algebra I, Springer, 1974. Chapter 3.
  4. J.-L. Koszul, Graded manifolds and graded Lie algebras, Proceedings of the international meeting on geometry and physics (Florence, 1982), 1983, pp. 71–84.
  5. Martin Moskowitz, An extension of Minkowski’s theorem to simply connected 2-step nilpotent groups, Port. Math. 67 (2010), no. 4, 541–546.
  6. ———, The triangle inequality for graded real vector spaces of length 3 and 4, Math. Inequal. Appl. 17 (2014), no. 3, 1027–1030.
  7. Steven Roman, Advanced linear algebra, Third, Graduate Texts in Mathematics, vol. 135, Springer, New York, 2008.
  8. S. Salami and T. Shaska, Local and global heights on weighted projective varieties, Houston J. Math. 49 (2023), no. 3, 603–636 (English).
  9. ———, Vojta’s conjecture on weighted projective varieties (2024), available at arXiv:2309.10300.
  10. E. Shaska and T. Shaska, Machine learning for moduli space of genus two curves (2024), available at arXiv:2403.17250.
  11. Songpon Sriwongsa and Keng Wiboonton, The triangle inequality for graded real vector spaces, Math. Inequal. Appl. 23 (2020), no. 1, 351–355.
  12. Maurice Weiler, Patrick Forré, Erik Verlinde, and Max Welling, Equivariant and coordinate independent convolutional networks, University of Amsterdam, 2023.

All preprints