Fetching the paper…

Reading the bibliography…

2019

Output-Constrained Bayesian Neural Networks

Yang, Wanqian, Lorch, Lars, Graule, Moritz A. et al.

Original
PDF
Post on X

Understand

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.

Output-Constrained Bayesian Neural Networks · Around

Built on

Probable networks and plausible predictions – a review of practical bayesian methods for supervised neural networks
MacKay, D. J. C · 1995
Earlier work this paper cites.
Bayesian Learning for Neural Networks
Neal, R. M · 1995
Earlier work this paper cites.
Defining functional shoulder range of motion for activities of daily living
Namdari, S., Yagnik, G., Ebaugh, D. D., Nagda, S., Ramsey, M. L., Williams Jr, G. R., and Mehta, S · 2012
Earlier work this paper cites.
Mcmc using hamiltonian dynamics
Neal, R. M · 2012
Earlier work this paper cites.

Similar

Mimic-iii, a freely accessible critical care database
Johnson, A. E., Pollard, T. J., Shen, L., Li-wei, H. L., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Celi, L. A., and Mark, R. G · 2016
Cited alongside, same era.
Stein variational gradient descent: A general purpose bayesian inference algorithm
Liu, Q. and Wang, D · 2016
Cited alongside, same era.
Reliable uncertainty estimates in deep neural networks using noise contrastive priors
Original
Hafner, D., Tran, D., Lillicrap, T., Irpan, A., and Davidson, J · 2018
Cited alongside, same era.
Towards combining motion optimization and data driven dynamical models for human motion prediction
Kratzer, P., Toussaint, M., and Mainprice, J · 2018
Cited alongside, same era.

Then

Constraining the dynamics of deep probabilistic models
Original
Lorenzi, M. and Filippone, M · 2018
Later among the works it cites.
mocap-mlr-datasets
Kratzer, P · 2019
Closest in time.
Functional variational bayesian neural networks
Original
Sun, S., Zhang, G., Shi, J., and Grosse, R · 2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…