News & Views | Published:

Artificial intelligence

Deep neural reasoning

Nature volume 538, pages 467468 (27 October 2016) | Download Citation

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

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

References

  1. 1.

    Cogn. Sci. 4, 135–183 (1980).

  2. 2.

    & (eds) Perspectives of Neural–Symbolic Integration (Springer, 2007).

  3. 3.

    et al. Nature 538, 471–476 (2016).

  4. 4.

    J. Math. 58, 345–363 (1936).

  5. 5.

    , & Nature 521, 436–444 (2015).

  6. 6.

    et al. Proc. IEEE Conf. Computer Vision Pattern Recognition (2015).

  7. 7.

    , & Int. Conf. Learning Representations Preprint at (2014).

  8. 8.

    & Machine Learn. 100, 5–47 (2015).

  9. 9.

    , & Preprint at (2014).

Download references

Author information

Affiliations

  1. Herbert Jaeger is at Jacobs University Bremen, 28759 Bremen, Germany.

    • Herbert Jaeger

Authors

  1. Search for Herbert Jaeger in:

Corresponding author

Correspondence to Herbert Jaeger.

About this article

Publication history

Published

DOI

https://doi.org/10.1038/nature19477

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Newsletter Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing