Output-Constrained Bayesian Neural Networks
This work addresses the challenge of making Bayesian neural networks more interpretable and reliable for practitioners in domains like healthcare and robotics, though it is incremental as it builds on existing BNN frameworks.
The authors tackled the problem of encoding prior knowledge in function space for Bayesian neural networks by formulating a prior that incorporates functional constraints on outputs, demonstrating improved model robustness and prevention of infeasible predictions in healthcare and robotics applications.
Bayesian neural network (BNN) priors are defined in parameter space, making it hard to encode prior knowledge expressed in function space. We formulate a prior that incorporates functional constraints about what the output can or cannot be in regions of the input space. Output-Constrained BNNs (OC-BNN) represent an interpretable approach of enforcing a range of constraints, fully consistent with the Bayesian framework and amenable to black-box inference. We demonstrate how OC-BNNs improve model robustness and prevent the prediction of infeasible outputs in two real-world applications of healthcare and robotics.