DeepAI AI Chat
Log In Sign Up

Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families

by   Seong Jae Hwang, et al.
University of Wisconsin-Madison

There has recently been a concerted effort to derive mechanisms in vision and machine learning systems to offer uncertainty estimates of the predictions they make. Clearly, there are enormous benefits to a system that is not only accurate but also has a sense for when it is not sure. Existing proposals center around Bayesian interpretations of modern deep architectures -- these are effective but can often be computationally demanding. We show how classical ideas in the literature on exponential families on probabilistic networks provide an excellent starting point to derive uncertainty estimates in Gated Recurrent Units (GRU). Our proposal directly quantifies uncertainty deterministically, without the need for costly sampling-based estimation. We demonstrate how our model can be used to quantitatively and qualitatively measure uncertainty in unsupervised image sequence prediction. To our knowledge, this is the first result describing sampling-free uncertainty estimation for powerful sequential models such as GRUs.


page 3

page 9

page 10

page 11


Convolutional Deep Exponential Families

We describe convolutional deep exponential families (CDEFs) in this pape...

Accurate Uncertainties for Deep Learning Using Calibrated Regression

Methods for reasoning under uncertainty are a key building block of accu...

Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs

Uncertainty quantification is crucial for building reliable and trustabl...

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

Whereas the ability of deep networks to produce useful predictions on ma...

Uncertainty in Structured Prediction

Uncertainty estimation is important for ensuring safety and robustness o...

Tailored Uncertainty Estimation for Deep Learning Systems

Uncertainty estimation bears the potential to make deep learning (DL) sy...