Metraipolis › archive › dc_e4188b53ca2e

Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex — arXiv:2608.12408

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12408
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:45.720Z
SHA-256 of the archived text
4759b79fb6b508f446c35dec166b659a84f030be96616976f31bf56391a5cce6
Stable URL of this page
https://metraipolis.com/documento/dc_e4188b53ca2e

How to cite

Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex — arXiv:2608.12408 — arXiv (en), https://arxiv.org/abs/2608.12408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4188b53ca2e (Metraipolis archive dc_e4188b53ca2e, sha256 4759b79fb6b508f446c35dec166b659a84f030be96616976f31bf56391a5cce6)
BibTeX
@misc{dce4188b53ca2e,
  title = {Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex — arXiv:2608.12408},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12408},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4188b53ca2e; sha256 4759b79fb6b508f446c35dec166b659a84f030be96616976f31bf56391a5cce6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Studies of biologically plausible learning rules (feedback alignment, predictive coding, STDP) train small networks on $32\times32$ images and compare them with brain responses to naturalistic stimuli presented at much higher resolution. We find that a common result in this setting, that untrained or locally trained networks rival or beat backpropagation at early visual cortex, depends on the resolution at which networks are evaluated. In representational similarity analysis (RSA) against human V1, the gap between an untrained and a backprop-trained network grows monotonically from $-0.001$ (95% CI $[-0.011, 0.009]$) at the 32 px training resolution to $+0.030$ $[0.018, 0.042]$ at 224 px (six resolutions, 5 seeds; per-subject RSA on cross-run stimulus pairs). The growth reproduces for three further learning rules, directionally in single-seed macaque electrophysiology, along training, and for an ImageNet ResNet-50 and a Swin-Tiny transformer, which also align best at low resolution although trained at 224 px. Gabor and pixel structure, the normalization state of the untrained baseline, and a global brightness statistic do not account for it. Against a criterion fixed before the analysis, limiting image content to 32 px while the input still grows does not shrink the V1 gap ($+0.035$ $[0.023, 0.046]$ vs. $+0.030$ at 224 px; ratio 1.14 $[1.03, 1.34]$): it arises once the input exceeds the training resolution, through a decline of backprop. A single luminance value per image reaches $\rho = 0.054$ against V1, matching the untrained network (0.053), which bounds what RSA on globally pooled features can resolve at V1 in this dataset. The one learning effect that holds across resolution is backprop above untrained at LOC. Comparisons of learning rules or architectures at early visual cortex need to control, and report, the evaluation resolution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Neurons and Cognition (q-bio.NC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.12408 — 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 2026-10-19T04:20:35.880Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).