Discovering dependencies in complex physical systems using Neural Networks
In todays age of data, discovering relationships between different variables is an interesting and a challenging problem. This problem becomes even more critical with regards to complex dynamical systems like weather forecasting and econometric models, which can show highly non-linear behavior. A method based on mutual information and deep neural networks is proposed as a versatile framework for discovering non-linear relationships ranging from functional dependencies to causality. We demonstrate the application of this method to actual multivariable non-linear dynamical systems. We also show that this method can find relationships even for datasets with small number of datapoints, as is often the case with empirical data.
Code (0)
등록된 구현이 없습니다.
Tasks
Weather ForecastingSimilar Papers 제목 키워드 기반
Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
The great learning ability of deep learning models facilitates us to comprehend the real physical world, making learning to simulate complicated particle systems a promising endeavour. However, the complex laws of the ph…
Correcting model misspecification in physics-informed neural networks (PINNs)
Data-driven discovery of governing equations in computational science has emerged as a new paradigm for obtaining accurate physical models and as a possible alternative to theoretical derivations. The recently developed …
Discovering Conservation Laws using Optimal Transport and Manifold Learning
Conservation laws are key theoretical and practical tools for understanding, characterizing, and modeling nonlinear dynamical systems. However, for many complex systems, the corresponding conserved quantities are difficu…
Discovering Phase Transitions with Unsupervised Learning
Unsupervised learning is a discipline of machine learning which aims at discovering patterns in big data sets or classifying the data into several categories without being trained explicitly. We show that unsupervised le…
ClusteringCausal discovery for time series with latent confounders
Reconstructing the causal relationships behind the phenomena we observe is a fundamental challenge in all areas of science. Discovering causal relationships through experiments is often infeasible, unethical, or expensiv…
Causal DiscoveryTime SeriesTime Series Analysis