Artificial intelligence systems have struggled to understand common-sense laws of the physical world, even though this ‘intuitive physics’ is rapidly acquired by young humans. Piloto et al. demonstrate that a deep learning system closely modelled on infant cognition outperforms the more traditional ‘learning from scratch’ systems.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
Turing, A. Mind 69, 433–460 (1950).
Piloto, L. S., Weinstein, A., Battaglia, P. & Botvinick, M. Nat. Hum. Behav. https://doi.org/10.1038/s41562-022-01394-8 (2022).
Hespos, S. J. & Baillargeon, R. Cognition 78, 207–245 (2001).
Needham, A. & Baillargeon, R. Cognition 47, 121–148 (1993).
Spelke, E. S., Breinlinger, K., Macomber, J. & Jacobson, K. Psychol. Rev. 99, 605–632 (1992).
Spelke, E. S. Cogn. Sci. 14, 29–56 (1990).
Spelke, E. S. & Kinzler, K. D. Dev. Sci. 10, 89–96 (2007).
Thelen, E. & Smith, L. B. A Dynamic Systems Approach to the Development of Cognition and Action (MIT Press, 1996).
Gopnik, A. Science 337, 1623–1627 (2012).
Oakes, L. M. & Rakison, D. H. Developmental Cascades (Oxford Univ. Press, 2020).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Hespos, S., Shivaram, A. Can a computer think like a baby?. Nat Hum Behav 6, 1191 (2022). https://doi.org/10.1038/s41562-022-01395-7
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41562-022-01395-7
