Search papers, labs, and topics across Lattice.
This paper introduces a variational Bayesian inference framework that incorporates linear equality constraints directly into the learning process. The method enforces linear relationships between inputs and outputs while providing full predictive uncertainty over model parameters and domain knowledge. Experiments on a single-particle battery model demonstrate that the proposed approach reduces credible intervals and constraint violations compared to standard Bayesian neural networks.
Guaranteeing physical constraints in your ML model doesn't have to sacrifice uncertainty quantification – this Bayesian method bakes in linear equalities while shrinking credible intervals.
Machine Learning is becoming more prevalent in science and engineering, but many approaches do not provide meaningful uncertainty estimates and predictions may also violate known physical knowledge. We propose a Bayesian framework to embed linear relationships across inputs and outputs into the learning process, whilst characterizing full predictive uncertainty over both the model parameters and the domain knowledge. We evaluated our method on learning the single particle battery model subject to voltage and energy balances, showing its ability to provide reduced credible intervals and constraint violations compared to standard Bayesian neural networks based on variational inference.
