Metraipolis › archive › dc_a820f7164609

Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks — arXiv:2611.03597

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03597
License (as archived): CC0-1.0
Archived: 2026-11-03T11:26:52.112Z
SHA-256 of the archived text: 902f8bc6fdc8608f271f7d846f721650a2a821448999ec3bf8047b5048bec5a2
Stable URL of this page: https://metraipolis.com/documento/dc_a820f7164609

How to cite

Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks — arXiv:2611.03597 — arXiv (en), https://arxiv.org/abs/2611.03597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a820f7164609 (Metraipolis archive dc_a820f7164609, sha256 902f8bc6fdc8608f271f7d846f721650a2a821448999ec3bf8047b5048bec5a2)

BibTeX

@misc{dca820f7164609,
  title = {Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks — arXiv:2611.03597},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03597},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a820f7164609; sha256 902f8bc6fdc8608f271f7d846f721650a2a821448999ec3bf8047b5048bec5a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain. We propose a structured visual representations landscape and design an activation-based prior that allows us to effectively regularize the landscape with activations from brain regions or neural network units. Our model Vis-Lens integrates a variational autoencoder and a diffusion model into an image generation framework. It enables the generation of natural, realistic preferred images by directly modifying the activation-regularized latent codes without per-image iterative optimization. We demonstrate the effectiveness of our framework on both artificial neural networks and human visual cortex using functional magnetic resonance imaging (fMRI) data. Our framework improves activation modulation and image realism compared with a recent state-of-the-art method for generating preferred visual representations of these neural targets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2611.03597 — 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 2026-11-03T11:02:37.921Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).