Metraipolis › archive › dc_c8ebd7570128

Geometric and algebraic inference in humans and neural networks — arXiv:2611.00387

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00387
License (as archived)
CC0-1.0
Archived
2026-11-03T10:45:53.256Z
SHA-256 of the archived text
83bd02a643445c1dea10e479768cede46a9d1728c6a63fd43a9772a6b470f4c3
Stable URL of this page
https://metraipolis.com/documento/dc_c8ebd7570128

How to cite

Geometric and algebraic inference in humans and neural networks — arXiv:2611.00387 — arXiv (en), https://arxiv.org/abs/2611.00387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8ebd7570128 (Metraipolis archive dc_c8ebd7570128, sha256 83bd02a643445c1dea10e479768cede46a9d1728c6a63fd43a9772a6b470f4c3)
BibTeX
@misc{dcc8ebd7570128,
  title = {Geometric and algebraic inference in humans and neural networks — arXiv:2611.00387},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00387},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8ebd7570128; sha256 83bd02a643445c1dea10e479768cede46a9d1728c6a63fd43a9772a6b470f4c3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humans possess a remarkable ability to draw inferences from limited data. While some inferences are made intuitively from past experience, others require online reasoning based on novel information given in context. Here, we formalize these strategies, which we term geometric and algebraic inference, and study their computational tradeoffs in humans and neural networks. The geometric strategy gradually shapes representational geometry to reflect underlying relational structure, making subsequent inference cheap. The algebraic strategy flexibly attends to and reasons over novel relations given in context, but costs additional computation at inference time. We identify opposing signatures of these two strategies in transitive inference, a domain widely studied across species, and characterize the conditions under which each is observed. Our framework predicts that the geometric strategy should be dominant when relations are familiar, whereas the algebraic should emerge to support de novo inferences drawn in context. Multiple experiments demonstrate these opposing signatures in humans, neural networks trained from scratch, and large language models (LLMs). Causal interventions in the neural networks reveal that the geometric and algebraic strategies depend on representational geometry and selective attention mechanisms, respectively, and reproduce the effects of analogous neurobiological disruptions in humans. Our framework unifies these effects with disparate phenomena, including content effects observed in human and LLM reasoning and data-distribution effects observed in machine learning. Our findings reconcile competing views of cognitive flexibility that emphasize either representational geometry or algebraic manipulation by showing that each can have unique strengths, and can characterize different aspects of both human and neural network behavior.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Neurons and Cognition (q-bio.NC) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00387 — 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 2026-11-03T10:39:50.399Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).