Metraipolis › archive › dc_652da7fe0450

Curriculum unlearning in humans and neural networks — arXiv:2611.04565

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04565
License (as archived): CC0-1.0
Archived: 2026-11-04T21:51:39.763Z
SHA-256 of the archived text: 7a3d15af62aa86331e2a8391a57139f511b4f62a01746a17535b79477f135724
Stable URL of this page: https://metraipolis.com/documento/dc_652da7fe0450

How to cite

Curriculum unlearning in humans and neural networks — arXiv:2611.04565 — arXiv (en), https://arxiv.org/abs/2611.04565 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_652da7fe0450 (Metraipolis archive dc_652da7fe0450, sha256 7a3d15af62aa86331e2a8391a57139f511b4f62a01746a17535b79477f135724)

BibTeX

@misc{dc652da7fe0450,
  title = {Curriculum unlearning in humans and neural networks — arXiv:2611.04565},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04565},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_652da7fe0450; sha256 7a3d15af62aa86331e2a8391a57139f511b4f62a01746a17535b79477f135724},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04565. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2611.04565 — 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 2026-11-04T21:38:49.718Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).