ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias
Deep learning models are able to approximate one specific dynamical system but struggle at learning generalisable dynamics, where dynamical systems obey the same laws of physics but contain different numbers of elements (e.g., double- and triple-pendulum systems). To relieve this issue, we proposed the Modular Lagrangian Network (ModLaNet), a structural neural network framework with modularity and physical inductive bias. This framework models the energy of each element using modularity and then construct the target dynamical system via Lagrangian mechanics. Modularity is beneficial for reusing trained networks and reducing the scale of networks and datasets. As a result, our framework can learn from the dynamics of simpler systems and extend to more complex ones, which is not feasible using other relevant physics-informed neural networks. We examine our framework for modelling double-pendulum or three-body systems with small training datasets, where our models achieve the best data efficiency and accuracy performance compared with counterparts. We also reorganise our models as extensions to model multi-pendulum and multi-body systems, demonstrating the intriguing reusable feature of our framework.
Code (1)
Tasks
Inductive BiasSimilar Papers 제목 키워드 기반
Softly Induced Functional Simplicity: Implications for Neural Network Generalisation, Robustness, and Distillation
Learning robust and generalisable abstractions from high-dimensional input data is a central challenge in machine learning and its applications to high-energy physics (HEP). Solutions of lower functional complexity are k…
Soft Geometric Inductive Bias for Object Centric Dynamics
Equivariance is a powerful prior for learning physical dynamics, yet exact group equivariance can degrade performance if the symmetries are broken. We propose object-centric world models built with geometric algebra neur…
Physically Consistent Neural ODEs for Learning Multi-Physics Systems
Despite the immense success of neural networks in modeling system dynamics from data, they often remain physics-agnostic black boxes. In the particular case of physical systems, they might consequently make physically in…
Physical Imitation Learning: Distilling Control Policies into Passive Elasticity
Due to brain-body co-evolution, animals' intrinsic body dynamics play a crucial role in their energy-efficient locomotion. Specifically, the control effort is shared between active muscles and passive body dynamics--a pr…
Reinforcement LearningSEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases
Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate c…