A classic question in cognitive science is whether learning requires innate, domain-specific inductive biases to solve visual tasks. A recent study trained machine-learning systems on the first-person visual experiences of children to show that visual knowledge can be learned in the absence of innate inductive biases about objects or space.
This is a preview of subscription content, log in via an institution to check access.
References
Orhan, A. E. & Lake, B. M. Nat. Mach. Intell. https://doi.org/10.1038/s42256-024-00802-0 (2024).
Azevedo, F. A. C. et al. J. Comp. Neurol. 513, 532–541 (2009).
Adolph, K. E. et al. Trends Cogn. Sci. 22, 699–711 (2018).
Dosovitskiy, A. et al. In 9th Int. Conf. Learning Representations https://openreview.net/forum?id=YicbFdNTTy (2021).
Zhuang, C. et al. Proc. Natl Acad. Sci. USA 118, e2014196118 (2021).
Sheybani, S., Hansaria, H., Wood, J. N., Smith, L., & Tiganj, Z. In 37th Conf. Neural Information Processing Systems https://openreview.net/forum?id=zkfyOkBVpz (2023).
Pandey, L., Wood, S. M. W., & Wood, J. N. In 36th Conf. Neural Information Processing Systems https://openreview.net/forum?id=W23ZTdsabj (2023).
Smith, L. B., Jayaraman, S., Clerkin, E. & Yu, C. Trends Cogn. Sci. 22, 325–336 (2018).
Kuhn, T. The Structure of Scientific Revolution (Univ. Chicago Press, 1962).
Buckner, C. From Deep Learning to Rational Machines (Oxford Univ. Press, 2023).
Tong, Z., Song, Y., Wang, J., & Wang, L. In 36th Conf. Neural Information Processing Systems https://openreview.net/forum?id=AhccnBXSne (2022).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The author declares no competing interests.
Rights and permissions
About this article
Cite this article
Wood, J.N. Artificial intelligence tackles the nature–nurture debate. Nat Mach Intell 6, 381–382 (2024). https://doi.org/10.1038/s42256-024-00828-4
Published:
Issue Date:
DOI: https://doi.org/10.1038/s42256-024-00828-4
- Springer Nature Limited