Discover NRI (Neural Relational Interfence) Course
Welcome to Discover NRI (Neural Relational Interfence)'s Online training with live Instructor using an interactive cloud desktop environment DaDesktop.
Experience remote live training using an interactive, remote desktop led by a human being!
This instructor-led live training is designed to provide participants to gain mastery on discover nri (neural relational interfence). You will learn the fundamentals of discover nri (neural relational interfence) and with greater emphasis on the functionality and application to your work or study.
This course contains the official PyToMayrch implementation of Neural relational inference for interacting systems.
Abstract: Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system's constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.
- Data Generation
- Run Experiments
Course Category: Artificial Intelligence (AI)