Skip to main content
SpringerLink
Log in

Algorithm discovery

Distilling data into code

  • News & Views
  • Published:

From Nature Computational Science

View current issue Submit your manuscript

One of the greatest limitations of deep neural networks is the difficulty of interpreting what they learn from the data. Deep distilling addresses this problem by extracting human-comprehensible and executable code from observations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1: Deep distilling architecture.

References

  1. Blazek, P. J., Venkatesh, K. & Lin, M. M. Nat. Comput. Sci. https://doi.org/10.1038/s43588-024-00593-9 (2024).

    Article  PubMed  Google Scholar 

  2. Blazek, P. J. & Lin, M. M. Nat. Comput. Sci. 1, 607–618 (2021).

    Article  PubMed  Google Scholar 

  3. Langley, P. Scientific Discovery: Computational Explorations of the Creative Processes (MIT Press, 1987).

  4. Xu, F. et al. Explainable AI: A brief survey on history, research areas, approaches and challenges. In Natural Language Processing and Chinese Computing. NLPCC 2019 (eds Tang, J. et al.) Lecture Notes in Computer Science Vol 11839, 563–574 (Springer, 2019).

  5. Karniadakis, G. E. et al. Nat. Rev. Phys. 3, 422–440 (2021).

    Article  Google Scholar 

  6. Brunton, S. L., Proctor, J. L. & Kutz, J. N. Proc. Natl Acad. Sci. 113, 3932–3937 (2016).

    Article  ADS  CAS  PubMed  PubMed Central  Google Scholar 

  7. McCulloch, W. S. & Pitts, W. Bull. Math. Biophys. 5, 115–133 (1943).

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. American University of Beirut, Beirut, Lebanon

    Joseph Bakarji

Authors
  1. Joseph Bakarji
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joseph Bakarji.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bakarji, J. Distilling data into code. Nat Comput Sci 4, 92–93 (2024). https://doi.org/10.1038/s43588-024-00598-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s43588-024-00598-4

  • Springer Nature America, Inc.

Search

Navigation