1 code implementation • 29 Sep 2022 • Satya Borgohain, Klaus Ackermann, Ruben Loaiza-Maya
Probabilistic predictions from neural networks which account for predictive uncertainty during classification is crucial in many real-world and high-impact decision making settings.
no code implementations • 30 Jul 2021 • Lachlan O'Neill, Simon Angus, Satya Borgohain, Nader Chmait, David L. Dowe
While some methods for combining these exist in the literature, our architecture generalizes these approaches by taking interactions into account, offering the power of a dense neural network without forsaking interpretability.