Metraipolis › archive › dc_5233cefee071

AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn — arXiv:2610.40757

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40757
License (as archived): CC0-1.0
Archived: 2026-11-03T07:52:12.593Z
SHA-256 of the archived text: 8b373547c3f65fe1af7c8108fb5c832ad9634991d507e3f81fed2f3eaa517914
Stable URL of this page: https://metraipolis.com/documento/dc_5233cefee071

How to cite

AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn — arXiv:2610.40757 — arXiv (en), https://arxiv.org/abs/2610.40757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5233cefee071 (Metraipolis archive dc_5233cefee071, sha256 8b373547c3f65fe1af7c8108fb5c832ad9634991d507e3f81fed2f3eaa517914)

BibTeX

@misc{dc5233cefee071,
  title = {AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn — arXiv:2610.40757},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40757},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5233cefee071; sha256 8b373547c3f65fe1af7c8108fb5c832ad9634991d507e3f81fed2f3eaa517914},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humans and animals have a unique capacity to generalize and learn in novel circumstances, including "0-shot" inference (ZI) and continual learning (CL) -- two powerful cognitive abilities. Despite this importance, efforts to model ZI and CL are seriously limited in several ways. First, existing models typically lack components critical to ZI and CL in the brain, namely, strong inductive biases (for ZI) and autonomous control of learning (for CL). Second, models can be less tractable to analysis if model components are overly complex (lacking simplicity), or too task-restricted if model components are overly bespoke (lacking expressivity). Here we introduce autonomous Hebbian networks ("AutoHebb"), a class of online learning feedforward neural networks that realize strong inductive biases and autonomously controlled learning, and are both simple and expressive. Unlike standard models that learn via externally controlled optimization (e.g. gradient descent), AutoHebb networks combine external feedback with internally generated activity to produce a global learning signal ('neuromodulator') fed back to the network. The neuromodulator in turn gates a biologically grounded local learning rule (3-factor Hebbian rule) that updates networks' plastic weights. Using meta-learning to search for fixed (non-plastic) weights, we find that AutoHebb networks (1) succeed on ZI tasks, (2) show emergent (untrained) ZI/CL abilities, (3) admit reverse-engineering into explicit algorithms, and (4) outperform modern learning models on ZI/CL tasks. Lastly, performance comparisons to related models implied an essential role for three model components: meta-learning, Hebbian plasticity, and autonomous control of learning. These findings indicate that AutoHebb may be useful in hypothesis generation, analysis, and discovery of biologically grounded forms of learning and generalization.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2610.40757 — 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 2026-11-03T07:49:31.114Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).