Sampling-based Bayesian Inference with gradient uncertainty

Abstract

Deep neural networks(NNs) have achieved impressive performance, often exceed human performance on many computer vision tasks. However, one of the most challenging issues that still remains is that NNs are overconfident in their predictions, which can be very harmful when this arises in safety critical applications. In this paper, we show that predictive uncertainty can be efficiently estimated when we incorporate the concept of gradients uncertainty into posterior sampling. The proposed method is tested on two different datasets, MNIST for in-distribution confusing examples and notMNIST for out-of-distribution data. We show that our method is able to efficiently represent predictive uncertainty on both datasets.

arXiv commentPresented at the Workshop on Bayesian Deep Learning, NeurIPS 2018, Montréal, Canada

References in corpus (4)

• Weight Uncertainty in Neural Networks
• Stochastic Gradient Hamiltonian Monte Carlo
• Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
• Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization

Cited by in corpus (5)

• How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
• The Unreasonable Effectiveness of Deep Evidential Regression
• Towards calibrated and scalable uncertainty representations for neural networks
• A Financial Service Chatbot based on Deep Bidirectional Transformers
• Multivariate Deep Evidential Regression