Summary of Learning Governing Equations Of Unobserved States in Dynamical Systems, by Gevik Grigorian et al.
Learning Governing Equations of Unobserved States in Dynamical Systems
by Gevik Grigorian, Sandip V. George, Simon Arridge
First submitted to arxiv on: 29 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to learn governing equations of partially-observed dynamical systems using a hybrid neural ordinary differential equation (ODE) structure and symbolic regression. The method combines domain-specific knowledge with a neural network to describe system dynamics, which is then used to infer the true underlying equations of unobserved states. The authors test this approach on two case studies: the Lotka-Volterra system and the Lorenz system, demonstrating robustness to measurement noise. This work has implications for data-driven modelling and scientific machine learning in dynamical systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using math and computers to learn how things change over time. Right now, we’re good at learning from complete data, but what if some of the information is missing? The authors created a new way to figure this out by mixing together special computer programs called neural networks with other knowledge we already have. They tested it on two examples: a model of animal populations and weather patterns. It worked well even when there was noise in the data! This could be important for scientists who want to understand how things change over time. |
Keywords
» Artificial intelligence » Machine learning » Neural network » Regression
