Journal ArticleDOI
Multi-objective symbolic regression for physics-aware dynamic modeling
TLDR
This paper considers a multi-objective symbolic regression method that optimizes models with respect to their training error and the measure of how well they comply with the desired physical properties and proposes an extension to the existing algorithm that helps generate a diverse set of high-quality models.Abstract:
Virtually all dynamic system control methods benefit from the availability of an accurate mathematical model of the system. This includes also methods like reinforcement learning, which can be vastly sped up and made safer by using a dynamic system model. However, obtaining a sufficient amount of informative data for constructing dynamic models can be difficult. Consequently, standard data-driven model learning techniques using small data sets that do not cover all important properties of the system yield models that are partly incorrect, for instance, in terms of their steady-state characteristics or local behavior. However, often some knowledge about the desired physical properties of the model is available. Recently, several symbolic regression approaches making use of such knowledge to compensate for data insufficiency were proposed. Therefore, this knowledge should be incorporated into the model learning process to compensate for data insufficiency. In this paper, we consider a multi-objective symbolic regression method that optimizes models with respect to their training error and the measure of how well they comply with the desired physical properties. We propose an extension to the existing algorithm that helps generate a diverse set of high-quality models. Further, we propose a method for selecting a single final model out of the pool of candidate output models. We experimentally demonstrate the approach on three real systems: the TurtleBot 2 mobile robot, the Parrot Bebop 2 drone and the magnetic manipulation system. The results show that the proposed model-learning algorithm yields accurate models that are physically justified. The improvement in terms of the model’s compliance with prior knowledge over the models obtained when no prior knowledge was involved in the learning process is of several orders of magnitude.read more
Citations
More filters
Journal ArticleDOI
A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge
TL;DR: SciMED as discussed by the authors combines a wrapper selection method, based on a genetic algorithm, with automatic machine learning and two levels of symbolic regression (SR) methods to discover meaningful symbolic expressions from the data.
Proceedings ArticleDOI
Interaction-transformation evolutionary algorithm with coefficients optimization
TL;DR: Four different strategies to optimize the coefficients of the nonlinear part of the Interaction-Transformation representation are proposed and shown that optimizing the non-linear and linear coefficients separately was the best strategy to find better-performing expressions with a higher run-time and expression size.
Journal ArticleDOI
Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives
TL;DR: Symbolic regression (SR) as discussed by the authors is a machine learning-based regression method based on genetic programming principles that integrates techniques and processes from heterogeneous scientific fields and is capable of providing analytical equations purely from data.
Journal ArticleDOI
A multiobjective prediction model with incremental learning ability by developing a multi-source filter neural network for the electrolytic aluminium process
TL;DR: In this article , a multi-source filter neural network (MSFNN) was proposed for the electrolytic aluminum process (EAP) to improve current efficiency and reduce energy consumption.
Journal ArticleDOI
Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)
TL;DR: The main advantage of PAFs was in the more efficient constraining and interleaving of PINNs with the investigating physical phenomena and their underlying mathematical models.
References
More filters
Journal ArticleDOI
A fast and elitist multiobjective genetic algorithm: NSGA-II
TL;DR: This paper suggests a non-dominated sorting-based MOEA, called NSGA-II (Non-dominated Sorting Genetic Algorithm II), which alleviates all of the above three difficulties, and modify the definition of dominance in order to solve constrained multi-objective problems efficiently.
Book
Genetic Programming: On the Programming of Computers by Means of Natural Selection
TL;DR: This book discusses the evolution of architecture, primitive functions, terminals, sufficiency, and closure, and the role of representation and the lens effect in genetic programming.
Journal ArticleDOI
Distilling Free-Form Natural Laws from Experimental Data
Michael D. Schmidt,Hod Lipson +1 more
TL;DR: In this article, the authors proposed a method for automatically searching motion-tracking data captured from various physical systems, ranging from simple harmonic oscillators to chaotic double-pendula, without any prior knowledge about physics, kinematics, or geometry, the algorithm discovered Hamiltonians, Lagrangians, and other laws of geometric and momentum conservation.
Supporting Online Material for Distilling Free-Form Natural Laws from Experimental Data
Michael Schmidt,Hod Lipson +1 more
TL;DR: This work proposes a principle for the identification of nontriviality, and demonstrated this approach by automatically searching motion-tracking data captured from various physical systems, ranging from simple harmonic oscillators to chaotic double-pendula, and discovered Hamiltonians, Lagrangians, and other laws of geometric and momentum conservation.
Proceedings Article
PILCO: A Model-Based and Data-Efficient Approach to Policy Search
TL;DR: PILCO reduces model bias, one of the key problems of model-based reinforcement learning, in a principled way by learning a probabilistic dynamics model and explicitly incorporating model uncertainty into long-term planning.