Metraipolis › archive › dc_7b8724bd4cda
The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity — arXiv:2609.26940
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26940
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:57:47.970Z
- SHA-256 of the archived text
5b5a63e6817923ed13e5a7943aa3ba31b5926de88999c637ae7b5d3458f9627c- Stable URL of this page
https://metraipolis.com/documento/dc_7b8724bd4cda
How to cite
The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity — arXiv:2609.26940 — arXiv (en), https://arxiv.org/abs/2609.26940 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b8724bd4cda (Metraipolis archive dc_7b8724bd4cda, sha256 5b5a63e6817923ed13e5a7943aa3ba31b5926de88999c637ae7b5d3458f9627c)
BibTeX
@misc{dc7b8724bd4cda,
title = {The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity — arXiv:2609.26940},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26940},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b8724bd4cda; sha256 5b5a63e6817923ed13e5a7943aa3ba31b5926de88999c637ae7b5d3458f9627c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26940. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Biological sensory neurons have selective receptive fields organized along meaningful stimulus coordinates, such as frequency, motion direction, or retinotopic position. Such structure may arise from efficient coding and biological constraints on activity, connectivity, and wiring, as computational studies of simple neurons have shown across modalities. This raises a question: do structured receptive fields confer a computational advantage beyond resource efficiency itself, and does this advantage persist when individual neurons are highly expressive? We address this question in recurrent networks of Expressive Leaky Memory neurons, where we can independently vary neuronal complexity and the organization of feed-forward receptive fields. Across auditory and event-based visual classification tasks, receptive fields aligned with a task-relevant sensory coordinate improve test accuracy relative to budget-matched random receptive fields. This advantage disappears when sensory coordinates are scrambled, or when receptive fields follow task-irrelevant coordinates, showing that the benefit comes from alignment with task geometry rather than restricted connectivity alone. Increasing neuronal complexity reduces the performance advantage of structured receptive fields. Finally, generic synaptic sparsity regularization induces input selectivity and partially recovers performance, but remains substantially below explicitly structured receptive fields, suggesting that sparsity alone is insufficient to recover the full computational benefit of task-aligned receptive fields. Together, our results show that appropriate receptive fields can serve as a computational prior beyond sparsity itself, and that their value depends on the computational expressivity of individual neurons. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC). Pagina del lavoro: https://arxiv.org/abs/2609.26940 — 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 2026-10-08T10:06:16.791Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).