Output-Constrained Bayesian Neural Networks

*Yang, W.**,
Lorch, L.*,
Graule, M. A.*,
Srinivasan, S.,
Suresh, A.,
Yao, J.,
Pradier, M. F.,
and Doshi-Velez, F.

In *36th International Conference on Machine Learning Workshop on Uncertainty and Robustness in Deep Learning*,
2019.

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.