Deep learning driven model discovery in biology and physics

Lecture by Remy Kusters, long term research fellow at CRI, as part of the cycle "Sciences in Context" organized by CRI and the IAS in Paris.

Presentation

Sciences in Context is a series of public lectures, organized by Muriel Mambrini and Pascal Kolbe, in collaboration with the Institut d'études avancées de Paris, aimed at bringing SHS concepts and perspectives to the CRI community.
The topics of the conference will be discussed at a public session of the Practical Philosophy Club on the Friday before each conference, in order to encourage discussion with the guest speaker.

Subject of the conference

As scientific data sets become richer and increasingly complex, machine learning (ML) tools become more useful and widely applied. Discovering a mechanistic model, rather than predicting the outcome is paramount in the scientific endeavor and its lack in present day ML is limiting further integration of ML in quantitative science. In this talk I will present our development of quantitative tools to extract human interpretable models from quantitative biological and physical data sets. The work combines the predictive power of neural networks with the interpretability of symbolic regression to develop a framework of interpretable AI and discover mechanistic models from biological and physical data.