{
  "abstract": "During learning, humans often benefit from curricula that teach simple rules before exceptions. However, we lack a computational explanation for this phenomenon. Here, using a canonical behavioural task and modelling with neural networks, we develop and test a theory for why simple-to-complex curricula succeed. We show that during learning, both humans and neural networks show simplicity biases, a tendency to learn simple rules that are underfit to the data. In neural networks this bias is accompanied by compression of neural representations. Simple-to-complex curricula help both types of learners overcome this compression, developing representations (and policy) with appropriate dimensionality for the task. We test and confirm a further prediction from this theory: learners that have been pre-exposed to simple tasks and with more compressed initial representations benefit more from curricula. These findings suggest that curricula help with ``unlearning'' of simple rules.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.04565",
  "author_total": 4,
  "authors": [
    {
      "name": "Jirko Rubruck"
    },
    {
      "name": "Alice Zhang"
    },
    {
      "name": "Andrew Saxe"
    },
    {
      "name": "Christopher Summerfield"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f3yczq5v3mg73.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.04565",
  "fulltext_url": null,
  "id": "f3yczq5v3mg73",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.04565",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.04565",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f3yczq5v3mg73.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T15:21:30Z",
      "native_id": "2611.04565",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.04565"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Curriculum unlearning in humans and neural networks",
  "title_text": "Curriculum unlearning in humans and neural networks",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:04Z",
  "url": "https://research.draconitic.com/paper/f3yczq5v3mg73",
  "venue": "arXiv",
  "versions": []
}