What Uncertainties Do We Need for Dynamical Systems?
The distinction between aleatoric and epistemic uncertainty has received considerable attention in machine learning research, mainly in the context of supervised learning but also in other settings such as generative modeling. In this paper, we offer a machine learning perspective on uncertainty modeling for dynamical systems, which has been studied much less so far. In particular, we ask: what uncertainties do we need for dynamical systems? We discuss sources of uncertainty, clarify their nature (aleatoric or epistemic), and consider how the objectives of representing and quantifying uncertainty vary across different tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Predictions and Decision Making for Resilient Intelligent Sustainable Energy Systems
Future energy systems are subject to various uncertain influences. As resilient systems they should maintain a constantly high operational performance whatever happens. We explore different levels and time scales of deci…
Decision MakingPhysics-Enhanced Machine Learning: a position paper for dynamical systems investigations
This position paper takes a broad look at Physics-Enhanced Machine Learning (PEML) -- also known as Scientific Machine Learning -- with particular focus to those PEML strategies developed to tackle dynamical systems' cha…
Decision MakingPositionActive Perception Applied To Unmanned Aerial Vehicles Through Deep Reinforcement Learning
Unmanned Aerial Vehicles (UAV) have been standing out due to the wide range of applications in which they can be used autonomously. However, they need intelligent systems capable of providing a greater understanding of w…
Contrastive LearningDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change
Autonomous systems operating in the real world encounter a range of uncertainties. Probabilistic neural Lyapunov certification is a powerful approach to proving safety of nonlinear stochastic dynamical systems. When face…
Lyapunov-Based Deep Neural Networks for Adaptive Control of Stochastic Nonlinear Systems
Controlling nonlinear stochastic dynamical systems involves substantial challenges when the dynamics contain unknown and unstructured nonlinear state-dependent terms. For such complex systems, deep neural networks can se…