CoChat
Sign Up
Cited by 67Machine Learning and AlgorithmsDomain Adaptation and Few-Shot LearningReinforcement Learning in Robotics

Lessons from infant learning for unsupervised machine learning

Open access
Zaadnoordijk, Lorijn, Besold, Tarek R., Cusack, Rhodri·2022·Nature Machine Intelligence
DOI 10.1038/s42256-022-00488-2
Open this paper in CoChat — free accountOpen PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s42256-022-00488-2

Cites

172 of 172 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Intrinsically motivated behaviors facilitate unsupervised learning without explicit external rewards or punishments, offering advantages in early developmental stages.

    “Such behaviors facilitate unsupervised learning without explicit external rewards or punishments, which is known to offer various advantages in early developmental stages (White 1959; Gopnik 2009; Zaadnoordijk et al. 2022; Kanazawa et al. 2023).”

    From Emergence of Goal‐Directed Behaviors via Active Inference With Self‐Prior (2026) · cites this paper as Zaadnoordijk et al. 2022

    The section on infants’ curiosity-driven learning (page unavailable) says infants actively direct attention toward learning opportunities and describes curiosity as optimal for learning. The paper also presents active learning as a factor in infants’ early learning, but the passages do not establish the claim’s specific contrast with explicit external rewards or punishments. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 173 references couldn’t be matched to a known paper.

Research works printed but not linked: 30

  1. Baldi, P. Autoencoders, unsupervised learning and deep architectures. In Proc. ICML Workshop on Unsupervised and Transfer Learning (eds.
  2. Guyon, I., Dror, G., Lemaire, V., Taylor, G. & Silver, D.) 37-49 (JMLR, 2012).
  3. Ren, S., He, K., Girshick, R. & Sun, J. Faster R-CNN: towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems Vol. 28 (eds. Cortes, C., Lawrence, N., Lee, D., Sugiyama, M. & Garnett, R.) 91-99 (NIPS, 2015).
  4. Huh, M., Agrawal, P. & Efros, A. A. What makes ImageNet good for transfer learning? Preprint at https://arxiv.org/abs/1608.08614 (2016). · arXiv
  5. Recht, B., Roelofs, R., Schmidt, L. & Shankar, V. Do ImageNet classifiers generalize to imagenet? In Proc. 36th International Conference on Machine Learning (eds.
  6. Chaudhuri, K. & Salakhutdinov, R.) 5389-5400 (PMLR, 2019).
  7. Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In Proc. 37th International Conference on Machine Learning (eds. Daumé, H. III & Singh, A.) 1597-1607 (PMLR, 2020).
  8. Zbontar, J., Jing, L., Misra, I., LeCun, Y. & Deny, S. Barlow twins: self-supervised learning via redundancy reduction. In Proc. 38th International Conference on Machine Learning (eds.
  9. Meila, M. & Zhang, T.) 12310-12320 (PMLR, 2021).
  10. Ma, W. J. & Peters, B. A neural network walks into a lab: towards using deep nets as models for human behavior. Preprint at https://arxiv.org/ abs/2005.02181 (2020). · arXiv
  11. Bengio, Y. Deep learning of representations for unsupervised and transfer learning. In Proc. ICML Workshop on Unsupervised and Transfer Learning (eds.
  12. Guyon, I., Dror, G., Lemaire, V., Taylor, G. & Silver, D.) 17-36 (JMLR, 2012).
  13. Kidd, C. How to know. In Proc. 33rd Conference on Neural Information Processing Systems (NIPS, 2019).
  14. Hunnius, S. Early cognitive development: five lessons from infant learning. In Oxford Research Encyclopedia of Psychology (ed.
  15. Braddick, O.) (Oxford Univ. Press, in the press).
  16. Braddick, O., Atkinson, J. & Innocenti, G. M.) 173-193 (Elsevier, 2011).
  17. Linsley, D., Kim, J., Ashok, A. & Serre, T. Recurrent neural circuits for contour detection. In Proc. 8th International Conference on Learning Representations (ICLR, 2020).
  18. Michalski, R. S. in Machine Learning 83-134 (Morgan Kaufmann, 1983).
  19. Feinman, R. & Lake, B. M. Learning inductive biases with simple neural networks. In Proc. 40th Annual Meeting of the Cognitive Science Society (eds.
  20. Kopparti, R. M. & Weyde, T. Weight priors for learning identity relations. In Advances in Neural Information Processing Systems Vol. 33 (eds. Wallach, H. M., Larochelle, H., Beygelzimer, A., d' Alché-Buc, F. E. Fox, A. & Garnett, R.) (NIPS, 2020).
  21. Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097-1105 (2012).
  22. Hitzler, P. & Sarker, M. K.) 1-51 (IOS Press, 2021).
  23. d' Avila Garcez, A. S. & Gabbay, D. M. Fibring neural networks. In Proc. Nineteenth National Conference on Artificial Intelligence, Sixteenth Conference on Innovative Applications of Artificial Intelligence (eds.
  24. McGuinness, D. L. & Ferguson, G.) 342-347 (AAAI Press/MIT Press, 2004).
  25. Radford, A., Metz, L. & Chintala, S. Unsupervised representation learning with deep convolutional generative adversarial networks. In Proc. 4th International Conference on Learning Representations (eds.
  26. Getoor, L. & Scheffer, T.) 689-696 (Omnipress, 2011). 122. Srivastava, N. & Salakhutdinov, R. R. Multimodal learning with deep Boltzmann machines. In Advances in Neural Information Processing Systems (Pereira, F., Burges, C. J., Bottou, L. & Weinberger, K. Q.) 2222-2230 (NIPS, 2012). 123.
  27. Bachman, P., Hjelm, R. D. & Buchwalter, W. Learning representations by maximizing mutual information across views. In Advances in Neural Information Processing Systems (eds.
  28. Boutilier, C.) 1273-1278 (Morgan Kaufmann, 2009). 127. Wang, C. & Mahadevan, S. Heterogeneous domain adaptation using manifold alignment. In Proc. Twenty-Second International Joint Conference on Artificial Intelligence Vol. 2 (ed. Walsh, T.) 1541-1546 (AAAI Press, 2011). 128.
  29. Fiser, J., Aslin, R., Lathrop, A., Rothkopf, C. & Markant, J. An infants' eye view of the world: implications for learning in natural contexts. In Proc. International Conference on Infant Studies (2006). 141.
  30. Javed, K. & White, M. Meta-learning representations for continual learning. In Advances in Neural Information Processing Systems (eds.

Cited by

Sorted by citations

Related

Authors
Zaadnoordijk, L., Besold, T. R., & Cusack, R.
Affiliations
  • Trinity College Dublin (IE)
  • Eindhoven University of Technology (NL)
Corresponding author
Besold, Tarek R.
ORCID
Venue
Nature Machine Intelligence
Publisher
Springer Science and Business Media LLC
Published
2022-06-22
Volume
4
Issue
6
Pages
510-520
ISSN
2522-5839 (ISSN-L)
DOI
10.1038/s42256-022-00488-2
OpenAlex
W4283266503
Cited by
65
References
173
Citations by year
2026: 6 · 2025: 15 · 2024: 18 · 2023: 25 · 2022: 1
FWCI
4.85
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Machine Intelligence (publishedVersion)
  • TU/e Research Portal (publishedVersion, other-oa)
  • TU/e Research Portal (submittedVersion, other-oa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
Keywords
unsupervised learning, infant cognition, developmental science, experiential learning, algorithm design, annotated dataset

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review