Integrating machine learning and multiscale modeling-perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences.
Alber M, Buganza Tepole A, Cannon WR, De S, Dura-Bernal S, Garikipati K, Karniadakis G, Lytton WW, Perdikaris P, Petzold L, Kuhl E. · 2019
Read Integrating machine learning and multiscale modeling-perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences. by Alber M, Buganza Tepole A, Cannon WR, De S, Dura-Bernal S, Garikipati K, Karniadakis G, Lytton WW, Perdikaris P, Petzold L, Kuhl E. (2019) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc6877584.txt.
Description
Alber and co-authors offer a perspective in NPJ Digital Medicine on joining two modelling cultures. Biology and medicine now gather data faster than anyone can interpret it. Machine learning finds patterns across mixed data with ease. Left alone, though, it can return answers that break the laws of physics. Multiscale modelling has the opposite profile: faithful to mechanism, but slow and narrow.
The authors argue the two belong together, especially for systems that stack scales from molecules to whole organs. Learning can fill unknown parameters inside mechanistic models, and models can discipline what learning proposes. They survey early successes in the biological and biomedical sciences. Challenges in data, computing, and training are set out honestly.
Catalog record
| CREATOR | Alber M, Buganza Tepole A, Cannon WR, De S, Dura-Bernal S, Garikipati K, Karniadakis G, Lytton WW, Perdikaris P, Petzold L, Kuhl E. |
|---|---|
| YEAR | 2019 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |