Metraipolis › archive › dc_eb34d3374344

Bidirectional representational alignment between biological and artificial neural networks — arXiv:2608.18244

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18244
License (as archived)
CC0-1.0
Archived
2026-10-18T13:44:57.286Z
SHA-256 of the archived text
46877e778d83b51c2070563346784e639c2015eda00506f93ca3f14355b30010
Stable URL of this page
https://metraipolis.com/documento/dc_eb34d3374344

How to cite

Bidirectional representational alignment between biological and artificial neural networks — arXiv:2608.18244 — arXiv (en), https://arxiv.org/abs/2608.18244 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb34d3374344 (Metraipolis archive dc_eb34d3374344, sha256 46877e778d83b51c2070563346784e639c2015eda00506f93ca3f14355b30010)
BibTeX
@misc{dceb34d3374344,
  title = {Bidirectional representational alignment between biological and artificial neural networks — arXiv:2608.18244},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18244},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb34d3374344; sha256 46877e778d83b51c2070563346784e639c2015eda00506f93ca3f14355b30010},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18244. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric: model representations predict neural responses much better than neural responses predict model representations. This asymmetry raises the question of whether representational geometry contributes to bidirectional representational alignment. We hypothesized that steering representational geometry during training can systematically influence bidirectional alignment. To test this hypothesis, we developed a computational framework that integrates spectral regularization with bidirectional predictivity analyses. As an initial demonstration, we evaluated our framework using self-supervised contrastive vision models. Steering the spectral geometry of the learned representations substantially increased reverse predictivity with modest reductions in forward predictivity, yielding a 55% relative improvement in bidirectional predictivity. These improvements were accompanied by reduced effective dimensionality and a reorganization of the shared representational subspace, within which forward and reverse predictivity became approximately symmetric at intermediate spectral exponents. Overall, these findings demonstrate that representational geometry can be systematically steered to modulate bidirectional representational alignment between biological and artificial neural networks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18244 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:41:17.921Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).