Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal
Not on the map. Why?
Abstract (arXiv)
Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering domains. This study explores the application of KAN in building physics, focusing on predictive modeling, knowledge discovery, and continuous learning. Through four case studies, we demonstrate KAN's ability to rediscover fundamental equations, approximate complex formulas, and capture time-dependent dynamics in heat transfer. While there are challenges in extrapolation and interpretability, we highlight KAN's potential to combine advanced modeling methods for knowledge augmentation, which benefits energy efficiency, system optimization, and sustainability assessments beyond the personal knowledge constraints of the modelers. Additionally, we propose a model selection decision tree to guide practitioners in appropriate applications for building physics.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 55 references that are in the map. First posted on arXiv 20 Oct 2024.
Builds on
13 of 55 references.
References · 13
- 2024KAN: Kolmogorov-Arnold Networkscited by 649
- 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
- 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 205
- 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 98
- 2023Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical lawscited by 55
- 2024GKAN: Graph Kolmogorov-Arnold Networkscited by 53
- 2016Neuro-symbolic representation learning on biological knowledge graphscited by 25
- 2021Physics Informed Neural Networks for Control Oriented Thermal Modeling of Buildingscited by 24
- 2024Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viabilitycited by 23
- 2022A hybrid-model approach for reducing the performance gap in building energy forecastingcited by 6
- 2023Continually learning out-of-distribution spatiotemporal data for robust energy forecastingcited by 5
- 2023Pathway toward prior knowledge-integrated machine learning in engineeringcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.