The human brain can solve highly abstract reasoning problems using a neural network that is entirely physical. The underlying mechanisms are only partially understood, but an artificial network provides valuable insight. See Article p.471
Notes
References
Newell, A. Cogn. Sci. 4, 135–183 (1980).
Hammer, B. & Hitzler, P. (eds) Perspectives of Neural–Symbolic Integration http://doi.org/fsrb8m (Springer, 2007).
Graves, A. et al. Nature 538, 471–476 (2016).
Turing, A. M. J. Math. 58, 345–363 (1936).
LeCun, Y., Bengio, Y. & Hinton, G. Nature 521, 436–444 (2015).
Szegedy, C. et al. Proc. IEEE Conf. Computer Vision Pattern Recognition http://dx.doi.org/10.1109/CVPR.2015.7298594 (2015).
Bahdanau, D., Cho, K. & Bengio, Y. Int. Conf. Learning Representations Preprint at http://arxiv.org/abs/1409.0473 (2014).
De Raedt, L. & Kimmig, A. Machine Learn. 100, 5–47 (2015).
Graves, A., Wayne, G. & Danihelka, I. Preprint at http://arxiv.org/abs/1410.5401 (2014).
Author information
Authors and Affiliations
Corresponding author
Related links
Related links
Related links in Nature Research
Computer science: Nanoscale connections for brain-like circuits
Rights and permissions
About this article
Cite this article
Jaeger, H. Deep neural reasoning. Nature 538, 467–468 (2016). https://doi.org/10.1038/nature19477
Published:
Issue Date:
DOI: https://doi.org/10.1038/nature19477
- Springer Nature Limited
This article is cited by
-
Deep Residual Networks’ Abstract Reasoning Performance on Raven’s Progressive Matrices
SN Computer Science (2021)