EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Achieving Occam’s razor: Deep learning for optimal model reduction

Botond B Antal, Anthony G Chesebro, Helmut H Strey, Lilianne R Mujica-Parodi, Corey Weistuch iD

PLOS Computational Biology · 2024

DOI: 10.1371/journal.pcbi.1012283 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2024. Verfasst von Botond B Antal und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Stony Brook University, Stony Brook, New York, United States of America. Hauptthemen laut MEDLINE: Deep Learning, Computational Biology. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIGMS NIH HHS, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

All fields of science depend on mathematical models. Occam’s razor refers to the principle that good models should exclude parameters beyond those minimally required to describe the systems they represent. This is because redundancy can lead to incorrect estimates of model parameters from data, and thus inaccurate or ambiguous conclusions. Here, we show how deep learning can be powerfully leveraged to apply Occam’s razor to model parameters. Our method, FixFit, uses a feedforward deep neural network with a bottleneck layer to characterize and predict the behavior of a given model from its input parameters. FixFit has three major benefits. First, it provides a metric to quantify the original model’s degree of complexity. Second, it allows for the unique fitting of data. Third, it provides an unbiased way to discriminate between experimental hypotheses that add value versus those that do not. In three use cases, we demonstrate the broad applicability of this method across scientific domains. To validate the method using a known system, we apply FixFit to recover known composite parameters for the Kepler orbit model and a dynamic model of blood glucose regulation. In the latter, we demonstrate the ability to fit the latent parameters to real data. To illustrate how the method can be applied to less well-established fields, we use it to identify parameters for a multi-scale brain model and reduce the search space for viable candidate mechanisms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningComputational BiologyHumansNeural Networks, ComputerBlood GlucoseAlgorithmsModels, TheoreticalModels, Biological

Substanzen

Blood Glucose

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Stony Brook University, Stony Brook, New York, United States of America.
  • Laufer Center for Physical and Quantitative Biology, Stony Brook University, Stony Brook, New York, United States of America.
  • Santa Fe Institute, Santa Fe, New Mexico, United States of America.
  • Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, United States of America.

ORCID-Profile: Corey Weistuch

Förderung

  • NCI NIH HHS
  • NIGMS NIH HHS
  • National Science Foundation
  • Baszucki Brain Research Fund
  • National Institute of Health
  • Marie-Josée Kravis Fellowship

Zitieren

APA

Antal, B. B., Chesebro, A. G., Strey, H. H., Mujica-Parodi, L. R., & Weistuch, C. (2024). Achieving Occam’s razor: Deep learning for optimal model reduction. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012283

Vancouver

Antal BB, Chesebro AG, Strey HH, Mujica-Parodi LR, Weistuch C. Achieving Occam’s razor: Deep learning for optimal model reduction. PLOS Computational Biology. 2024. doi:10.1371/journal.pcbi.1012283

BibTeX
@article{Antal2024,
  author = {Antal, Botond B and Chesebro, Anthony G and Strey, Helmut H and Mujica-Parodi, Lilianne R and Weistuch, Corey},
  title = {Achieving Occam’s razor: Deep learning for optimal model reduction},
  journal = {PLOS Computational Biology},
  year = {2024},
  doi = {10.1371/journal.pcbi.1012283}
}
Kostenlos starten →