1 code implementation • 24 Aug 2023 • Kai Brach, Beate Sick, Oliver Dürr
We demonstrate that our single-shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BNNs.
1 code implementation • 7 Jul 2020 • Kai Brach, Beate Sick, Oliver Dürr
We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.