Publication Details

SELECT * FROM publications WHERE Record_Number=11339
Reference TypeConference Proceedings
Author(s)Look, A.; Kandemir, M.
Year2019
TitleDifferential Bayesian Neural Nets
Journal/Conference/Book TitleNeurIPS Bayesian Workshop
AbstractNeural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose a Bayesian version of N-ODEs that enables well-calibrated quantification of prediction uncertainty, while maintaining the expressive power of their deterministic counterpart. We assign Bayesian Neural Nets (BNNs) to both the drift and the diffusion terms of a Stochastic Differential Equation (SDE) that models the flow of the activation map in time. We infer the posterior on the BNN weights using a straightforward adaptation of Stochastic Gradient Langevin Dynamics (SGLD). We illustrate significantly improved stability on two synthetic time series prediction tasks and report better model fit on UCI regression benchmarks with our method when compared to its non-Bayesian counterpart.

  

zum Seitenanfang