{
  "abstract": "Predictive Coding (PC) is an influential account of how brain representations emerge through hierarchical, local, self-supervised prediction-based learning, without requiring globally propagated error signals. Despite extensive evidence supporting PC, a striking paradox persists: computational models built on these biologically grounded principles have consistently failed to match state-of-the-art Deep Neural Networks in performance and brain-alignment. Here, we show that this paradox can be overcome. We introduce Predictive Brain Networks (PBNs), a hierarchical recurrent framework that implements local PC-based learning and achieves representational alignment with the human ventral visual stream matching or exceeding established vision models. Importantly, PBN top-down predictions encode unique, brain-aligned information not captured during bottom-up feature extraction, with this contribution increasing in locally trained variants. Further, PBNs substantially outperform existing PC-inspired networks on downstream classification tasks, reproduce key signatures of PC (with higher-level predictions shaping lower-level visual responses as observed in the primate cortex), and support uncertainty estimation. PBNs therefore close a longstanding gap in computational neuroscience by combining two properties that have been largely separated: the brain-inspired learning mechanisms of predictive coding and the representational power of modern deep networks. They provide a scalable framework for studying biologically grounded learning without sacrificing the capacity to produce rich neural representations.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.37327",
  "author_total": 3,
  "authors": [
    {
      "name": "Dirk Gütlin"
    },
    {
      "name": "Ryszard Auksztulewicz"
    },
    {
      "name": "Adrien Doerig"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9deajtk9n0xe1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.37327",
  "fulltext_url": null,
  "id": "9deajtk9n0xe1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.37327",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "2805|Visual perception and processing mechanisms"
    ]
  ],
  "openalex": "W7224118127",
  "pdf_url": "https://arxiv.org/pdf/2610.37327",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9deajtk9n0xe1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:56Z",
      "native_id": "2610.37327",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.37327"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Local learning is all you need: brain-aligned predictive coding networks",
  "title_text": "Local learning is all you need: brain-aligned predictive coding networks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:56Z",
  "url": "https://research.draconitic.com/paper/9deajtk9n0xe1",
  "venue": "arXiv",
  "versions": []
}