Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Points of Significance

Neural networks primer

Nature Methods volume 20, pages 165–167 (2023)Cite this article

Nature is often hidden, sometimes overcome, seldom extinguished. —Francis Bacon

In some statistical models the parameters are related to identifiable features of the system while in others the parameters are purely predictive and only the predicted output of the model has physical meaning. The latter kinds of predictive models are common in so-called ‘complex systems’, such as computer vision, sequence modeling, and associating ‘omics’ data with disease outcomes. One popular class of predictive models is artificial neural networks (ANNs), which underlie a broader class of methods known as ‘deep learning’.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it

$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Composition of functions enables nonlinear predictions.
Fig. 2: Computation graphs for basic neural networks.
Fig. 3: Visualization of neurons as pattern recognizers.

References

  1. Altman, N. & Krzywinski, M. Nat. Methods 12, 999–1000 (2015).

    Article  CAS  PubMed  Google Scholar 

  2. Lever, J., Krzywinski, M. & Altman, N. Nat. Methods 13, 541–542 (2016).

    Article  CAS  Google Scholar 

  3. Das, K., Krzywinski, M. & Altman, N. Nat. Methods 16, 451–452 (2019).

    Article  CAS  PubMed  Google Scholar 

  4. Dey, T. et al. Nat. Methods 19, 1513–1515 (2022).

    Article  CAS  PubMed  Google Scholar 

  5. Rosenblatt, F. Psychol. Rev. 65, 386–408 (1958).

    Article  CAS  PubMed  Google Scholar 

  6. Grewal, J. K., Krzywinski, M. & Altman, N. Nat. Methods 17, 121–122 (2020).

    Article  CAS  PubMed  Google Scholar 

  7. Lever, J., Krzywinski, M. & Altman, N. Nat. Methods 13, 703–704 (2016).

    Article  CAS  Google Scholar 

  8. Lever, J., Krzywinski, M. & Altman, N. Nat. Methods 13, 803–804 (2016).

    Article  CAS  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biomedical Data Science, Stanford University, Stanford, CA, USA

    Alexander Derry

  2. Canada’s Michael Smith Genome Sciences Centre, Vancouver, British Columbia, Canada

    Martin Krzywinski

  3. Department of Statistics, The Pennsylvania State University, State College, PA, USA

    Naomi Altman

Authors
  1. Alexander Derry
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Martin Krzywinski
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Naomi Altman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Martin Krzywinski.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Derry, A., Krzywinski, M. & Altman, N. Neural networks primer. Nat Methods 20, 165–167 (2023). https://doi.org/10.1038/s41592-022-01747-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41592-022-01747-1

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

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